© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    give something

    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
     to
    -2.09
    </i>
    -1.52
    簓
    -1.51
    not
    -1.48
    <h1>
    -1.48
     those
    -1.46
    no
    -1.45
     CALIFORNI
    -1.41
     into
    -1.41
    1
    -1.38
    POSITIVE LOGITS
    niosek
    1.71
     ofere
    1.65
     dekol
    1.57
     posses
    1.55
     alguna
    1.53
     banyo
    1.53
    putar
    1.52
    grunge
    1.51
     llama
    1.50
    犊
    1.48
    Activations Density 0.032%

    No Known Activations