© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    cave system, water temperature, faces

    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
    ев
    0.46
    8
    0.46
    اع
    0.45
    ⒏
    0.45
    อ
    0.44
    ৯
    0.44
    存放
    0.41
    豉
    0.41
    اق
    0.40
    فك
    0.40
    POSITIVE LOGITS
    ES
    0.64
    ST
    0.49
    GRADE
    0.49
     Natürlich
    0.49
    VE
    0.48
     автоматически
    0.48
    vega
    0.48
     Ogni
    0.48
    mathop
    0.47
     dilated
    0.47
    Activations Density 0.000%

    No Known Activations