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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82674
    Prev
    Next
    INDEX
    Explanations

    relying on

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

    This neuron specializes in spotting version‐control identifiers—long hexadecimal or numeric commit hashes and version numbers.

    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
     through
    -1.18
     睡
    -0.98
     púb
    -0.92
     touted
    -0.90
    PyTuple
    -0.88
     nestled
    -0.88
    Ư
    -0.87
     on
    -0.84
     fully
    -0.82
    ...
    -0.82
    POSITIVE LOGITS
     différente
    1.00
     zapro
    0.99
     determinados
    0.94
     Dennoch
    0.94
    ITCHEN
    0.93
     чувства
    0.93
    𝕪
    0.92
     appartenant
    0.91
    nowu
    0.91
     erhi
    0.91
    Activations Density 0.000%

    No Known Activations