Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3964
    Prev
    Next
    INDEX
    Explanations

    listening, thought, you

    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
    ي
    0.88
    า
    0.77
    ない
    0.76
    deki
    0.73
    ную
    0.72
     nomenclatura
    0.71
    此同时
    0.69
    IUM
    0.68
    ك
    0.68
    ないので
    0.68
    POSITIVE LOGITS
    and
    0.80
    he
    0.69
    ond
    0.68
    ੰਜ
    0.66
    ếc
    0.65
    нде
    0.63
    мани
    0.63
    jęcia
    0.63
    pp
    0.63
    ud
    0.62
    Activations Density 0.459%

    No Known Activations