© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129830
    Prev
    Next
    INDEX
    Explanations

    names followed by comma or semicolon

    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
     only
    -1.70
     these
    -1.64
     as
    -1.58
     B
    -1.55
     some
    -1.52
    '
    -1.52
     Each
    -1.49
    These
    -1.47
     M
    -1.43
     noticeably
    -1.43
    POSITIVE LOGITS
     remé
    2.09
     plafon
    2.00
     célè
    1.95
    €”
    1.95
    ⬈
    1.90
     fidé
    1.88
    lorin
    1.83
     régal
    1.80
    StandardCharsets
    1.75
    𓁹
    1.74
    Activations Density 0.125%

    No Known Activations