© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12206
    Prev
    Next
    INDEX
    Explanations

    require statements

    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
     from
    -1.80
     each
    -1.51
     to
    -1.23
     every
    -1.13
    :
    
    -1.10
     all
    -1.09
     саны
    -1.07
     when
    -1.05
     its
    -1.04
    SizedBox
    -1.03
    POSITIVE LOGITS
     故
    1.11
     gevaar
    1.09
    utando
    1.06
     geïsole
    1.05
     risico
    1.05
     canaux
    1.04
    マジで
    1.04
    рюкзак
    1.04
    Apre
    1.03
    待って
    1.03
    Activations Density 0.011%

    No Known Activations