© 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. 12-GEMMASCOPE-2-RES-262K
    7. 4296
    Prev
    Next
    INDEX
    Explanations

    diagonal lines and cuts

    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_12_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
    ństw
    0.95
    ußer
    0.87
    />}/>
    0.87
    要在
    0.84
    𝔹
    0.84
     population
    0.84
    BUT
    0.84
    塢
    0.84
    ɳ
    0.83
    تين
    0.83
    POSITIVE LOGITS
    ed
    1.23
     diagonals
    0.98
     diag
    0.98
    yl
    0.97
     нажмите
    0.96
    ালি
    0.93
     листь
    0.93
     vẻ
    0.91
     angolo
    0.89
    íp
    0.88
    Activations Density 0.039%

    No Known Activations