© 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. 89489
    Prev
    Next
    INDEX
    Explanations

    names, numbers, or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite

    circle, dots, listening

    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
    wai
    0.54
    ti
    0.51
    ifier
    0.50
    registro
    0.50
    titulo
    0.47
    reminder
    0.47
    t
    0.47
    dd
    0.47
    TextField
    0.46
    tiff
    0.46
    POSITIVE LOGITS
     épais
    0.51
     humides
    0.50
    خستان
    0.50
     função
    0.49
    ี
    0.48
     funktionieren
    0.47
     fonction
    0.46
     руках
    0.45
     ductile
    0.44
     funções
    0.44
    Activations Density 0.001%

    No Known Activations