© 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. 57451
    Prev
    Next
    INDEX
    Explanations

    items shipped

    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
    _
    -2.98
     \
    -2.61
    ).
    -2.47
    0
    -2.30
    ⩥
    -2.14
     Geruch
    -2.13
    mathrm
    -2.08
    <em>
    -2.08
     feinen
    -2.08
     Betracht
    -2.06
    POSITIVE LOGITS
     shipped
    2.41
     плани
    2.28
    は
    2.25
     participé
    2.20
     グリル
    2.11
     THERE
    2.06
     entret
    2.05
    开始
    2.05
     Their
    2.03
    ISATION
    2.02
    Activations Density 0.003%

    No Known Activations