© 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. 34-GEMMASCOPE-RES-131K
    7. 118656
    Prev
    Next
    INDEX
    Explanations

    star and numeric ratings

    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
     rating
    -1.10
    ★★★★★
    -1.09
     five
    -1.09
     Five
    -1.06
    Five
    -1.04
    rating
    -1.00
    five
    -0.92
     hundred
    -0.90
     cinque
    -0.90
     ratings
    -0.90
    POSITIVE LOGITS
    moduleId
    0.93
    Aktual
    0.92
     solides
    0.85
    gotta
    0.84
    Conten
    0.82
     kesk
    0.80
    צלחה
    0.79
     fuertes
    0.79
    STRONG
    0.78
     ③
    0.78
    Activations Density 0.014%

    No Known Activations