© 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. 68367
    Prev
    Next
    INDEX
    Explanations

    continuing with actions or plans

    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
    appellant
    -1.75
     polegadas
    -1.75
    xvi
    -1.74
    岌
    -1.73
     großer
    -1.70
     besonderes
    -1.69
    両方
    -1.67
     schönes
    -1.66
     kleines
    -1.64
     ciertos
    -1.63
    POSITIVE LOGITS
    我们
    2.13
     of
    1.70
    ack
    1.65
    >
    1.63
    the
    1.63
    ?”
    1.60
    ER
    1.53
    >
    1.51
    mut
    1.50
    are
    1.49
    Activations Density 0.008%

    No Known Activations