© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17130
    Prev
    Next
    INDEX
    Explanations

    classic, serious, or vintage vibes

    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
    點
    0.51
    sentiment
    0.45
    ローマ
    0.44
    語言
    0.44
    籟
    0.44
    custom
    0.43
    物質
    0.42
     ਮ
    0.42
    foreign
    0.42
    ோவின்
    0.41
    POSITIVE LOGITS
     which
    0.46
    危险
    0.46
    怀
    0.45
    这一
    0.45
     risques
    0.44
     vilket
    0.42
    owały
    0.41
     singleArray
    0.41
     whose
    0.41
    ссии
    0.40
    Activations Density 0.007%

    No Known Activations