© 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. 34-GEMMASCOPE-RES-131K
    7. 116145
    Prev
    Next
    INDEX
    Explanations

    code and licensing identifiers

    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
    ___
    -0.94
    ______
    -0.87
    .*;
    -0.85
    _______
    -0.82
    than
    -0.81
     вашей
    -0.80
    thu
    -0.78
    ふと
    -0.77
    nej
    -0.77
     most
    -0.77
    POSITIVE LOGITS
    Oe
    0.82
    izmus
    0.81
    Lois
    0.81
    FIS
    0.81
     "/",
    0.80
     Chomsky
    0.79
    Mixture
    0.79
    Oa
    0.77
    也可
    0.76
    jamento
    0.75
    Activations Density 0.003%

    No Known Activations