© 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. 44843
    Prev
    Next
    INDEX
    Explanations

    Bundle express csv

    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
    но
    1.10
    al
    1.01
    са
    0.99
    "]);
    0.96
    ниш
    0.96
     tranche
    0.95
    ;
    0.91
    ,
    0.85
     mortem
    0.85
    ၞ
    0.84
    POSITIVE LOGITS
     fleste
    1.02
     rethink
    1.01
    いま
    0.98
     âg
    0.96
     människor
    0.96
    래
    0.96
    렇
    0.95
     esterno
    0.95
     mennesker
    0.94
     escolas
    0.94
    Activations Density 0.000%

    No Known Activations