© 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. 31213
    Prev
    Next
    INDEX
    Explanations

    state level, individual parties, personalised gift

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

    discrete descriptions

    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
     intérieur
    0.50
    Na
    0.48
    Box
    0.47
     arriver
    0.47
    Changes
    0.46
    From
    0.46
    Nous
    0.46
    ::
    0.45
    artment
    0.45
     had
    0.45
    POSITIVE LOGITS
    shakespeare
    0.50
    忌
    0.44
    スプレイ
    0.44
    чая
    0.42
    াবলী
    0.42
    ಾಂಶ
    0.42
    ของผู้
    0.41
    proposed
    0.41
     servants
    0.41
    trashButton
    0.41
    Activations Density 0.000%

    No Known Activations