© 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. 160949
    Prev
    Next
    INDEX
    Explanations

    avoid further delay

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

    caressing hair; regex; location

    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
     suka
    0.54
     tujuan
    0.54
     cak
    0.53
     ziel
    0.52
     zdecyd
    0.49
    vani
    0.49
     	i
    0.48
     DIE
    0.48
     geführt
    0.47
     abomin
    0.47
    POSITIVE LOGITS
    locationX
    0.52
    ↵
    0.48
     بالنسبة
    0.45
    lerde
    0.44
     localities
    0.42
    ancements
    0.41
    抽取
    0.41
    탄소년
    0.41
    يريا
    0.40
    isers
    0.40
    Activations Density 0.000%

    No Known Activations