© 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. 70504
    Prev
    Next
    INDEX
    Explanations

    fun and comfort

    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
     or
    -1.41
     it
    -1.39
     to
    -1.25
     Dadurch
    -1.23
     two
    -1.20
     क्यों
    -1.18
     large
    -1.16
    名人
    -1.15
    憬
    -1.14
     much
    -1.13
    POSITIVE LOGITS
    4
    1.27
    跻
    1.25
     autorité
    1.23
    왠
    1.13
    一双
    1.11
    9
    1.09
    又不
    1.08
    来到了
    1.08
     العلاج
    1.08
     tervez
    1.06
    Activations Density 0.045%

    No Known Activations