© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6707
    Prev
    Next
    INDEX
    Explanations

    negative trends, reductions, or failures

    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
    ,
    0.61
    ni
    0.58
    na
    0.57
    seye
    0.57
    ،
    0.57
    ne
    0.54
    nd
    0.54
     detriment
    0.52
    ll
    0.49
     indicative
    0.49
    POSITIVE LOGITS
    alang
    0.59
     thiểu
    0.59
    ের
    0.57
    }}_{\
    0.55
    
    0.54
    ेड
    0.53
    ాల
    0.52
    ेक्स
    0.52
     существенно
    0.52
    ים
    0.50
    Activations Density 0.628%

    No Known Activations