© 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. 34-GEMMASCOPE-RES-131K
    7. 99253
    Prev
    Next
    INDEX
    Explanations

    function signatures

    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
     nachher
    -1.02
     entweder
    -1.02
    ];
    -1.01
     "
    -0.98
    providedIn
    -0.96
     [];
    -0.93
     wybrać
    -0.93
     einzeln
    -0.90
    r
    -0.88
    这几
    -0.87
    POSITIVE LOGITS
    1.29
    *

    1.28
     whoſe
    1.09
    Recept
    1.08
     secondi
    1.06
    Interes
    1.05
     uova
    1.05
     FUNC
    1.04
    EFIAPI
    1.03
     skak
    1.03
    Activations Density 0.021%
    No Known Activations