© 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. 93594
    Prev
    Next
    INDEX
    Explanations

    import statements and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    apeno
    -0.82
    ponenten
    -0.81
     Stru
    -0.80
    スパイ
    -0.79
    Cair
    -0.78
     Saxon
    -0.77
     democracia
    -0.77
    kowania
    -0.76
     Архи
    -0.76
     Wre
    -0.75
    POSITIVE LOGITS
    銚
    0.84
    oused
    0.77
    Possible
    0.75
    tranh
    0.74
     répond
    0.74
    aneers
    0.73
     FINISH
    0.73
    onthe
    0.72
    ^^^^^^^^
    0.71
    cloth
    0.71
    Activations Density 0.001%

    No Known Activations