© 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. 153
    Prev
    Next
    INDEX
    Explanations

    thing

    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
    ु
    1.97
    ER
    1.77
    ر
    1.64
    ure
    1.62
    DS
    1.62
    ков
    1.61
    od
    1.51
    ке
    1.51
    ﺱ
    1.51
    от
    1.50
    POSITIVE LOGITS
    り
    2.11
     else
    2.08
     vibhav
    1.88
    tedir
    1.86
    tions
    1.83
    ികിത്സ
    1.81
     annat
    1.77
    办法
    1.71
    től
    1.69
    wiście
    1.59
    Activations Density 0.103%

    No Known Activations