© 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. 30226
    Prev
    Next
    INDEX
    Explanations

    paid off

    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
    铨
    0.47
     andDevice
    0.47
    ຼ
    0.47
    ícím
    0.45
    鳇
    0.45
     olması
    0.44
     worldRank
    0.44
     йил
    0.43
     ্
    0.43
    谦
    0.43
    POSITIVE LOGITS
    L
    0.59
     is
    0.58
    s
    0.56
     the
    0.50
    J
    0.47
     are
    0.47
     to
    0.46
    down
    0.46
    by
    0.44
    PERT
    0.44
    Activations Density 0.002%

    No Known Activations