© 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. 77573
    Prev
    Next
    INDEX
    Explanations

    legal and technical contexts

    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
     Thra
    -0.71
    SECURE
    -0.68
    lication
    -0.68
     utilice
    -0.67
    uracy
    -0.66
     înd
    -0.66
    ✞
    -0.65
     измене
    -0.64
    Compound
    -0.63
    coes
    -0.63
    POSITIVE LOGITS
     uits
    0.78
    idak
    0.77
     MN
    0.71
     Alfredo
    0.69
     Tyler
    0.68
     MT
    0.68
    ٭
    0.67
     JA
    0.67
     couch
    0.66
    delivery
    0.66
    Activations Density 0.057%

    No Known Activations