© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67985
    Prev
    Next
    INDEX
    Explanations

    agreement, connection, or function

    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
     belang
    -1.52
     tafel
    -1.45
     groote
    -1.38
    important
    -1.37
    itizing
    -1.31
     formid
    -1.30
     honden
    -1.30
     valu
    -1.30
    abil
    -1.27
     klok
    -1.26
    POSITIVE LOGITS
     this
    1.64
     its
    1.50
     our
    1.41
     clínicos
    1.41
    ].
    1.34
    /*
    1.30
     has
    1.30
     profundo
    1.27
     інших
    1.27
    );
    1.23
    Activations Density 0.255%

    No Known Activations