© 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. 40125
    Prev
    Next
    INDEX
    Explanations

    a/any/typical/specific

    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
    sometimes
    -1.16
    issez
    -1.15
    抡
    -1.13
     certains
    -1.13
     チラ
    -1.12
     espes
    -1.11
    Ñ
    -1.11
    ABBA
    -1.06
    ísimas
    -1.06
     troisième
    -1.06
    POSITIVE LOGITS
     any
    1.59
     typical
    1.49
     usual
    1.44
     specific
    1.33
     actual
    1.30
     anything
    1.23
     current
    1.14
     traditional
    1.13
     normal
    1.08
    有任何
    1.06
    Activations Density 0.086%

    No Known Activations