© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    Form, window, drawing, shapes

    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
     stessa
    -1.12
     аккумулятор
    -1.05
     heureuse
    -0.98
     altavoz
    -0.93
    症状
    -0.93
     a
    -0.93
     personnalisée
    -0.92
    himp
    -0.91
    izzazioni
    -0.91
    ০
    -0.91
    POSITIVE LOGITS
    崭
    1.15
    ulas
    1.09
    それだけ
    1.07
     of
    1.05
    但也
    1.02
    :[],
    1.00
    雰囲気が
    1.00
    ambito
    0.99
    Lịch
    0.99
    fficients
    0.97
    Activations Density 0.000%

    No Known Activations