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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76537
    Prev
    Next
    INDEX
    Explanations

    dust tasting of forgotten stars or road

    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
     ಇತರ
    0.52
    ST
    0.51
     Shallow
    0.48
    COMP
    0.45
    𐰀
    0.45
     LI
    0.44
    يان
    0.44
    MA
    0.44
    ME
    0.44
     TED
    0.44
    POSITIVE LOGITS
    髦
    0.51
    攻击
    0.47
     меня
    0.45
    颜色
    0.44
     컬러
    0.44
    维生素
    0.42
    长老
    0.42
    ueling
    0.41
     사이즈
    0.41
    дови
    0.41
    Activations Density 0.012%

    No Known Activations