© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    water treatment

    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
     clín
    0.63
     Interact
    0.62
     dites
    0.62
     terap
    0.61
    ı
    0.60
    ill
    0.60
    ି
    0.60
    ones
    0.59
     pasien
    0.59
    ᆢ
    0.59
    POSITIVE LOGITS
    งาน
    0.73
    পালা
    0.62
    عکس
    0.61
    ાર
    0.59
     yılında
    0.58
     heißt
    0.57
     zahlreiche
    0.57
    ด์
    0.57
    をした
    0.57
    存于
    0.56
    Activations Density 0.007%

    No Known Activations