© 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. 67035
    Prev
    Next
    INDEX
    Explanations

    acts as

    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
     those
    -1.30
     from
    -1.29
     on
    -1.28
     in
    -1.27
    scienced
    -1.20
     család
    -1.20
     joyas
    -1.20
     tazas
    -1.19
     estaban
    -1.18
     helicópter
    -1.18
    POSITIVE LOGITS
     diriger
    1.23
     TICKETS
    1.20
     garcía
    1.19
     achat
    1.17
     chứa
    1.15
     vinos
    1.10
    毁灭
    1.10
     bébé
    1.10
     suport
    1.10
    ável
    1.09
    Activations Density 0.083%

    No Known Activations