© 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. 58207
    Prev
    Next
    INDEX
    Explanations

    words starting questions

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

    questions about what and how

    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
    ？）
    0.68
    ?”.
    0.64
    ?..
    0.63
    ()?
    0.63
    ?".
    0.63
    ？
    0.62
    ..?
    0.61
    ？」
    0.59
    ?»
    0.59
    ?")
    0.57
    POSITIVE LOGITS
     impacto
    0.45
     Bedeutung
    0.44
     G
    0.42
    Ethiop
    0.41
     Esp
    0.41
     Bayesian
    0.40
    G
    0.40
     Tief
    0.39
     AG
    0.39
     es
    0.38
    Activations Density 0.042%

    No Known Activations