© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102164
    Prev
    Next
    INDEX
    Explanations

    auto-generated content

    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
    籥
    -2.00
    犼
    -1.84
     animada
    -1.75
    躄
    -1.66
     hvis
    -1.64
     inconsciente
    -1.63
    茕
    -1.60
    )」
    -1.60
    ⌗
    -1.54
    ٞ
    -1.52
    POSITIVE LOGITS
     of
    2.58
    :
    2.00
     összefoglaló
    1.91
     from
    1.88
    妡
    1.84
    \"
    1.73
     medži
    1.72
     ponú
    1.71
     majú
    1.71
     Brought
    1.71
    Activations Density 0.007%

    No Known Activations