© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12237
    Prev
    Next
    INDEX
    Explanations

    contributor license

    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
     apreci
    -1.11
     varios
    -1.08
     turista
    -1.02
    länge
    -1.02
     lju
    -1.01
    TEXTURE
    -1.01
     Serviço
    -1.00
    Ƃ
    -1.00
    lentes
    -0.98
    だという
    -0.97
    POSITIVE LOGITS
     wrze
    1.18
    žený
    1.06
     of
    1.03
     ".";
    1.02
    回目の
    1.02
     improve
    0.99
    daille
    0.98
    กัด
    0.98
    wego
    0.96
     działa
    0.96
    Activations Density 0.006%

    No Known Activations