© 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. 26835
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text processing

    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
    軾
    0.45
    ARD
    0.44
     carn
    0.44
     wacht
    0.44
     Mac
    0.44
    ano
    0.43
     bread
    0.42
     multitask
    0.42
     carne
    0.41
     ocorr
    0.41
    POSITIVE LOGITS
     utilisateur
    0.49
    人为
    0.49
    ཋ
    0.48
    内外
    0.48
    锹
    0.47
     अनुवाद
    0.46
    نسب
    0.46
    ர்ப்பு
    0.46
    apaccay
    0.46
    务
    0.46
    Activations Density 0.001%

    No Known Activations