© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 877
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    desired
    0.70
    のこと
    0.64
     desired
    0.63
    旣
    0.63
    ოლოდ
    0.63
     ktorí
    0.62
    想
    0.62
     beliebt
    0.60
    ﺷ
    0.60
    ほしい
    0.58
    POSITIVE LOGITS
     entails
    0.78
     reduces
    0.76
     involves
    0.72
     menjadi
    0.71
     introduces
    0.71
     Reduces
    0.71
     includes
    0.71
     consists
    0.70
     becomes
    0.70
     يكون
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.