© 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. 138630
    Prev
    Next
    INDEX
    Explanations

    gravity and force

    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
    2
    0.51
    ਜ਼
    0.45
    【
    0.44
    する
    0.44
    ми
    0.43
    ]+
    0.42
    ，
    0.41
    ва
    0.41
    )-
    0.40
    미
    0.40
    POSITIVE LOGITS
     Wird
    0.55
     Bereiche
    0.49
     forc
    0.48
     ഭൂ
    0.47
     şeyler
    0.46
     spatially
    0.46
    রচনা
    0.46
     đất
    0.46
     Elemente
    0.45
     entlang
    0.44
    Activations Density 0.012%

    No Known Activations