© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1721
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Weir
    0.86
     Cunningham
    0.83
    ➣
    0.79
     Woodward
    0.78
     preservative
    0.78
     Coom
    0.76
     Crosby
    0.76
     Dow
    0.76
    cps
    0.76
    punch
    0.75
    POSITIVE LOGITS
    L
    1.91
     L
    1.85
    LS
    1.45
    Ls
    1.42
    LE
    1.41
    Л
    1.41
     Л
    1.41
    l
    1.40
    LT
    1.38
    LL
    1.37
    Activations Density 3.928%

    No Known Activations