© 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. 5970
    Prev
    Next
    INDEX
    Explanations

    What, How, Meaning

    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
    ridate
    0.64
    uradaki
    0.62
    ünschen
    0.61
    cparam
    0.61
    iscid
    0.61
    ágenes
    0.60
    fileID
    0.60
    :'],
    0.60
    estima
    0.60
    ნიშვნელ
    0.59
    POSITIVE LOGITS
     Instead
    0.64
     instead
    0.63
    Instead
    0.59
    0.59
    Because
    0.56
    ↵
    0.56
     because
    0.56
       
    0.55
     Because
    0.55
           
    0.54
    Activations Density 0.017%

    No Known Activations