© 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. 74223
    Prev
    Next
    INDEX
    Explanations

    strips of material

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

    The neuron flags any occurrence of the “strip”/“strips” stem (and its equivalents, e.g. the Russian “поло…ски”) in the text.

    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
    {
    -2.27
    0
    -2.09
    In
    -1.99
    ?”
    -1.95
    .
    -1.91
    𓍊
    -1.83
    ”
    -1.80
     devenus
    -1.79
    也很
    -1.71
    
    -1.67
    POSITIVE LOGITS
     clín
    2.13
    勦
    2.13
     включая
    1.95
     desarrol
    1.87
    </i>
    1.80
    ଃ
    1.77
     the
    1.76
     You
    1.76
     который
    1.74
    咐
    1.73
    Activations Density 0.017%

    No Known Activations