© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103657
    Prev
    Next
    INDEX
    Explanations

    matrix-vector multiplication

    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_16_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
    እን
    0.55
    explique
    0.54
    ੩
    0.54
    ༧
    0.53
    Ἥ
    0.52
    のように
    0.51
     ως
    0.51
    。
    0.50
     भारता
    0.50
    琇
    0.50
    POSITIVE LOGITS
    ra
    0.59
    in
    0.59
    2
    0.58
    lb
    0.54
    ول
    0.54
    جتما
    0.52
    ется
    0.51
    lg
    0.50
    1
    0.50
     phía
    0.50
    Activations Density 0.000%

    No Known Activations