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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1423
    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
     W
    0.98
    W
    0.97
     SW
    0.96
     WL
    0.93
     Wick
    0.93
     Dunn
    0.91
     WSA
    0.90
     Shaw
    0.89
     Stu
    0.89
    wpt
    0.88
    POSITIVE LOGITS
    akter
    0.92
    橿
    0.90
    ORIG
    0.88
     AKT
    0.82
    Rational
    0.82
    ак
    0.82
     Fujita
    0.81
     perfekt
    0.80
    perfect
    0.79
     racional
    0.79
    Activations Density 2.212%

    No Known Activations