© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1158
    Prev
    Next
    INDEX
    Explanations

    give you tailored advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    ,
    0.75
    ;
    0.67
     foundations
    0.66
     imbalances
    0.66
     હત્યા
    0.65
     –
    0.65
     At
    0.64
    fa
    0.63
    kit
    0.62
    ([],
    0.62
    POSITIVE LOGITS
    solved
    0.84
    మ్మ
    0.83
     שם
    0.80
     ']
    0.79
    優
    0.79
     ayudar
    0.79
    omore
    0.78
     agregó
    0.78
    도가
    0.78
     solución
    0.78
    Activations Density 0.223%

    No Known Activations