© 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. 10-GEMMASCOPE-RES-131K
    7. 7532
    Prev
    Next
    INDEX
    Explanations

    under Indiana law

    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_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
     when
    -1.76
     Then
    -1.59
     We
    -1.56
     "../../../../
    -1.51
    jenigen
    -1.49
    珢
    -1.48
     ,
    -1.45
    ignment
    -1.40
     if
    -1.38
     gesuchten
    -1.38
    POSITIVE LOGITS
     atriz
    1.98
     cantora
    1.59
     of
    1.52
    他不
    1.43
     других
    1.36
    を使
    1.35
    潆
    1.35
    她的
    1.35
    際は
    1.34
    好吃的
    1.34
    Activations Density 0.034%

    No Known Activations