© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27959
    Prev
    Next
    INDEX
    Explanations

    list items, mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тиви
    0.49
    REACTOR
    0.47
     характер
    0.46
     (\$
    0.46
    (":
    0.45
    ツアー
    0.44
    উদাহরণ
    0.44
    क्के
    0.44
    কান
    0.43
    चर
    0.43
    POSITIVE LOGITS
    ophobia
    0.43
     H
    0.40
     katalog
    0.40
     reik
    0.40
    klady
    0.39
     Whites
    0.39
    gató
    0.39
     P
    0.38
     â
    0.38
     radic
    0.38
    Activations Density 0.006%

    No Known Activations