© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 4613
    Prev
    Next
    INDEX
    Explanations

    symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ל
    0.82
    а
    0.81
    п
    0.75
    ﺭ
    0.69
    при
    0.66
     surprising
    0.65
    これを
    0.64
     ☐
    0.64
    يد
    0.64
    ぇ
    0.64
    POSITIVE LOGITS
    象征
    1.02
     symbol
    0.95
     symbolism
    0.92
     simbol
    0.91
     Symbol
    0.90
     symbolic
    0.89
     symbolizing
    0.89
     चिह्न
    0.86
    symbol
    0.85
    Symbol
    0.84
    Activations Density 0.003%

    No Known Activations