© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248477
    Prev
    Next
    INDEX
    Explanations

    updating, suggesting, recommending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tasting
    0.48
     tasting
    0.44
     Younger
    0.43
     Feast
    0.43
     Terrace
    0.42
     Gaud
    0.42
    燻
    0.42
    驕
    0.42
    fty
    0.41
     Sunshine
    0.41
    POSITIVE LOGITS
     direção
    0.57
     setor
    0.54
     dirigido
    0.54
    Benzoimidazol
    0.52
     almacenamiento
    0.50
     отношение
    0.49
     complejo
    0.48
     armazenamento
    0.48
     direccion
    0.47
     manajemen
    0.47
    Activations Density 0.000%

    No Known Activations