© 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. 8445
    Prev
    Next
    INDEX
    Explanations

    issues and problems

    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
     by
    -1.76
     –
    -1.64
     same
    -1.53
     -
    -1.45
    —
    -1.43
     "
    -1.36
     —
    -1.34
     '
    -1.30
     ‘
    -1.27
     the
    -1.27
    POSITIVE LOGITS
     ufficio
    1.52
     princesas
    1.45
    iest
    1.42
     tavolo
    1.38
     éstas
    1.37
     筒
    1.37
    ptures
    1.36
    ätie
    1.35
     acestea
    1.35
    ต้องการ
    1.35
    Activations Density 0.082%

    No Known Activations