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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35525
    Prev
    Next
    INDEX
    Explanations

    list items ending in parentheses

    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
    ->$
    -0.99
     needs
    -0.98
     said
    -0.94
     trzeba
    -0.94
    mphs
    -0.92
    }$,
    -0.91
    providedIn
    -0.91
    ΗΣ
    -0.89
    abstractmethod
    -0.89
     они
    -0.88
    POSITIVE LOGITS
     changement
    0.99
    meisters
    0.99
     oiseau
    0.96
    
    0.96
     prati
    0.94
     prairie
    0.94
    杀手
    0.94
     guld
    0.93
     noirs
    0.91
     paneles
    0.89
    Activations Density 0.004%

    No Known Activations