© 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. 59734
    Prev
    Next
    INDEX
    Explanations

    URLs and website paths

    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
     and
    -1.68
     in
    -1.67
     from
    -1.50
    parian
    -1.47
     not
    -1.47
    alata
    -1.43
     весна
    -1.42
    alpin
    -1.41
     antwoord
    -1.39
     including
    -1.38
    POSITIVE LOGITS
    賸
    1.84
     churras
    1.74
     alpes
    1.71
    ஂ
    1.65
     conos
    1.63
     dames
    1.63
     pajero
    1.63
     スーツ
    1.60
    ?」
    1.60
     rouges
    1.59
    Activations Density 0.079%

    No Known Activations