© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70319
    Prev
    Next
    INDEX
    Explanations

    motivations and intentions

    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
     the
    -1.86
     acogedor
    -1.57
     encantador
    -1.52
    лович
    -1.46
    mittag
    -1.46
     filósofo
    -1.44
    ―――
    -1.42
     jabón
    -1.41
    nappropriate
    -1.37
    photobucket
    -1.37
    POSITIVE LOGITS
     motives
    1.97
    oughed
    1.45
    ↵
    1.45
    1
    1.41
    migrationBuilder
    1.38
    8
    1.38
    ቍ
    1.36
    7
    1.34
    すすめ
    1.33
    之所
    1.32
    Activations Density 0.030%

    No Known Activations