© 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. 68288
    Prev
    Next
    INDEX
    Explanations

    reference point

    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
    ischof
    -2.22
     kterou
    -2.20
    idjan
    -2.19
     dijeron
    -2.11
     ayudan
    -2.09
     dicen
    -2.09
    oucí
    -2.00
    jenigen
    -1.97
     parecen
    -1.97
    aien
    -1.95
    POSITIVE LOGITS
    ↵
    2.98
    n
    2.50
    '
    2.50
    ーめん
    2.31
    寕
    2.28
     of
    2.25
    Ꮉ
    2.23
     \
    2.16
    ated
    2.14
    没想到
    2.14
    Activations Density 0.005%

    No Known Activations