© 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. 180625
    Prev
    Next
    INDEX
    Explanations

    dermo-epidermal junction

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

    menu: or columns:

    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
    治疗
    0.43
    ගේ
    0.43
     Haines
    0.42
    者は
    0.41
    治療
    0.41
    diver
    0.41
    咫
    0.40
     Jacobsen
    0.40
    <strong>
    0.39
     Hickey
    0.39
    POSITIVE LOGITS
     enchant
    0.54
    ン
    0.53
     ペンダント
    0.48
     meteorite
    0.47
     hexagons
    0.46
     identical
    0.45
     serio
    0.45
     unequivocal
    0.45
    ?
    0.45
     offert
    0.45
    Activations Density 0.000%

    No Known Activations