© 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-65K
    7. 20086
    Prev
    Next
    INDEX
    Explanations

    without

    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_65k_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
     बटे
    0.45
    де
    0.44
    Cotton
    0.44
    様子
    0.43
    п
    0.43
     கொள்ளலாம்
    0.43
    Puede
    0.41
    व
    0.41
    ลด
    0.41
    र
    0.41
    POSITIVE LOGITS
     senza
    0.59
     tanpa
    0.59
     zonder
    0.51
     resurrected
    0.49
     without
    0.49
     revived
    0.48
     permanently
    0.46
     unacceptable
    0.45
     endowment
    0.45
     Without
    0.44
    Activations Density 0.019%

    No Known Activations