© 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. 8267
    Prev
    Next
    INDEX
    Explanations

    numbers inside parentheses

    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
    juris
    0.36
    骸
    0.33
    gebäude
    0.33
     возникновения
    0.33
    applications
    0.32
    !:
    0.32
    
    0.32
    building
    0.32
     пользователя
    0.32
    実現
    0.31
    POSITIVE LOGITS
     ஆகிய
    0.37
     pourcentage
    0.36
     Một
    0.35
     sklearn
    0.34
     promedio
    0.34
     sigmoid
    0.32
    }
    0.32
     WITH
    0.32
     average
    0.31
     While
    0.31
    Activations Density 0.022%

    No Known Activations