© 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. 22-GEMMASCOPE-RES-131K
    7. 71748
    Prev
    Next
    INDEX
    Explanations

    attack and its immediate context

    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_22/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
    ’
    -3.09
    N
    -2.50
    a
    -2.39
    It
    -2.38
     -
    -2.30
    H
    -2.17
    Y
    -2.16
    and
    -2.11
    /
    -2.05
    from
    -2.02
    POSITIVE LOGITS
    kunjung
    2.72
    耵
    2.44
    пион
    2.30
     nieuwe
    2.28
     stycznia
    2.22
    chyma
    2.22
    诳
    2.19
    烔
    2.17
     considerada
    2.17
     waarde
    2.17
    Activations Density 0.015%

    No Known Activations