© 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. 4149
    Prev
    Next
    INDEX
    Explanations

    lists items joined by and

    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
     в
    0.65
     måde
    0.63
     veya
    0.62
     på
    0.58
     porta
    0.58
     was
    0.57
     åt
    0.57
     là
    0.57
     lä
    0.57
     bisa
    0.55
    POSITIVE LOGITS
    v
    0.59
    h
    0.58
    ކ
    0.55
    p
    0.53
    etc
    0.52
    x
    0.52
    jsdel
    0.51
    w
    0.50
    contracts
    0.50
    ނ
    0.50
    Activations Density 0.285%

    No Known Activations