© 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. 34-GEMMASCOPE-RES-131K
    7. 86797
    Prev
    Next
    INDEX
    Explanations

    contact alternatives

    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_34/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
    
    -1.49
    っていない
    -1.34
    sandalia
    -1.30
    
    -1.20
    敺
    -1.20
     Itália
    -1.20
    ᕮ
    -1.18
     eenige
    -1.17
     sudadera
    -1.16
    襌
    -1.16
    POSITIVE LOGITS
     by
    3.48
     through
    2.59
     via
    2.58
     visit
    2.41
     at
    2.31
     see
    2.14
     go
    1.98
     on
    1.98
     find
    1.86
     check
    1.85
    Activations Density 0.022%

    No Known Activations