© 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. 102503
    Prev
    Next
    INDEX
    Explanations

    one another

    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
    y
    -2.39
    Fär
    -2.34
    𔘓
    -2.31
    Mitar
    -2.17
     wth
    -2.08
    Berat
    -2.06
     Heilige
    -2.05
     กับ
    -2.02
     vois
    -1.96
    Läh
    -1.96
    POSITIVE LOGITS
    “
    2.73
    n
    2.59
     Then
    2.45
    甡
    2.31
    ز
    2.30
     There
    2.28
    м
    2.22
    ИН
    2.13
     –
    2.09
    ين
    2.09
    Activations Density 0.003%

    No Known Activations