Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14048
    Prev
    Next
    INDEX
    Explanations

    storyboarding

    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
    V
    0.92
    ↵
    0.88
    2
    0.87
    a
    0.86
    O
    0.86
    Style
    0.82
    se
    0.78
    Name
    0.77
    ه
    0.77
    ด์
    0.75
    POSITIVE LOGITS
     doua
    0.82
     spermatozoa
    0.77
     clockwise
    0.74
     fatti
    0.71
     acontecimientos
    0.71
     llave
    0.71
     posicao
    0.70
     terça
    0.70
     roupa
    0.70
     linhas
    0.68
    Activations Density 0.000%

    No Known Activations