© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100886
    Prev
    Next
    INDEX
    Explanations

    class names ending in Base

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "Base" in class names, particularly in inheritance declarations in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on the token “Base,” i.e. occurrences of the word “Base,” typically in class or type names indicating a base class.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Then
    -2.31
    м
    -2.19
     didnt
    -2.17
     These
    -2.09
     They
    -2.03
    各有
    -1.89
     trovano
    -1.88
     from
    -1.84
     trattano
    -1.84
     There
    -1.81
    POSITIVE LOGITS
    橚
    3.05
    Base
    2.34
    including
    2.27
    乄
    2.27
    齪
    2.23
    ﮦ
    2.22
    tact
    2.22
    嘚
    2.20
    6
    2.16
    ouſly
    2.14
    Activations Density 0.006%

    No Known Activations