© 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. 30917
    Prev
    Next
    INDEX
    Explanations

    columns and Columbia

    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
    ional
    2.20
    ılarak
    2.20
    ം
    2.02
    lerimiz
    1.95
    der
    1.92
    y
    1.89
    ra
    1.88
    い
    1.88
    nt
    1.84
    iton
    1.84
    POSITIVE LOGITS
    ור
    2.80
    મ
    2.52
    тор
    2.11
    Definitions
    2.06
    다른
    2.03
    нент
    2.02
    어
    2.02
    ка
    2.00
    ن
    2.00
     Ovaj
    1.95
    Activations Density 0.014%

    No Known Activations