© 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. 130952
    Prev
    Next
    INDEX
    Explanations

    formal procedures and descriptions

    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
     of
    -1.43
     If
    -1.29
     with
    -1.11
    what
    -1.09
     at
    -1.09
    If
    -1.09
     if
    -1.08
     .
    -1.06
    What
    -1.05
    ↵↵
    -1.04
    POSITIVE LOGITS
     lavabo
    1.22
     usarlo
    1.21
     Viena
    1.21
     emballage
    1.20
     meub
    1.20
     déli
    1.20
     Dette
    1.19
     biografi
    1.18
     ekonomi
    1.17
     maniere
    1.17
    Activations Density 0.244%

    No Known Activations