© 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. 13939
    Prev
    Next
    INDEX
    Explanations

    numbers and decimal points

    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
    Setelah
    -2.83
    Seperti
    -2.59
    Sebelum
    -2.52
    Beberapa
    -2.48
    Mereka
    -2.41
     говорили
    -2.41
    Menurut
    -2.38
    彼は
    -2.34
    Kemudian
    -2.30
    Meski
    -2.30
    POSITIVE LOGITS
    '
    2.83
    </sub>
    2.30
     of
    2.11
    ”
    2.11
    )’
    1.97
     —
    1.95
    蜘
    1.91
    ,’
    1.87
     suaves
    1.87
    selbe
    1.84
    Activations Density 0.046%

    No Known Activations