© 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. 67710
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
     its
    -1.53
     into
    -1.37
     either
    -1.29
     a
    -1.26
     the
    -1.14
     each
    -1.13
     of
    -1.08
    ченной
    -1.08
     an
    -1.04
     themselves
    -1.04
    POSITIVE LOGITS
    Текст
    1.20
     icke
    1.16
     pelic
    1.16
    بسم
    1.16
    鲥
    1.15
     patate
    1.13
    νή
    1.12
    Gö
    1.11
     vivre
    1.11
    Mvh
    1.11
    Activations Density 0.007%

    No Known Activations