© 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. 4207
    Prev
    Next
    INDEX
    Explanations

    gaze and direction

    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
    ن
    1.20
     restrictions
    1.14
     yksi
    1.04
     apari
    0.97
     faible
    0.96
     eaux
    0.95
     utilise
    0.94
     vantagens
    0.93
    ના
    0.93
     races
    0.92
    POSITIVE LOGITS
     👀
    1.12
     intently
    1.06
    và
    1.05
    𝑪
    1.02
    ">(</
    1.00
    👀
    1.00
    ៍
    0.99
    }$
    0.98
    áte
    0.96
    サングラス
    0.96
    Activations Density 0.293%

    No Known Activations