© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79070
    Prev
    Next
    INDEX
    Explanations

    entry budget value

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

    The neuron strongly responds to standalone numeric tokens—especially multi‐digit numbers used in technical specs or model identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    高端
    -0.85
    Innovative
    -0.82
    MacBook
    -0.81
     hầm
    -0.80
    𝙬
    -0.79
    Lamb
    -0.79
     flagship
    -0.78
    Limitation
    -0.78
     jugé
    -0.78
    旗
    -0.78
    POSITIVE LOGITS
     Entry
    1.09
     budget
    1.05
     entry
    1.04
     ENTRY
    0.98
    entry
    0.98
    Entry
    0.92
    budget
    0.92
     value
    0.91
     Basic
    0.91
     basic
    0.88
    Activations Density 0.058%

    No Known Activations