© 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. 96085
    Prev
    Next
    INDEX
    Explanations

    red bottom shoes websites

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

    limerick patterns

    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
    гда
    0.49
    婊
    0.47
    кин
    0.46
    ников
    0.44
    ๋า
    0.42
    круг
    0.42
    僚
    0.42
    ърква
    0.42
    濘
    0.42
     epidermal
    0.41
    POSITIVE LOGITS
    cad
    0.51
    of
    0.48
    terminated
    0.48
    rs
    0.48
    ton
    0.47
    val
    0.47
    ulfanyl
    0.46
    ies
    0.46
    with
    0.45
    ellige
    0.44
    Activations Density 0.002%

    No Known Activations