© 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. 320
    Prev
    Next
    INDEX
    Explanations

    value assignment

    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
    नरी
    1.45
    न
    1.45
    mall
    1.45
    lens
    1.43
     glycolysis
    1.41
    lith
    1.38
     elastomers
    1.37
    larda
    1.36
    lari
    1.34
    lion
    1.32
    POSITIVE LOGITS
     currentLocation
    1.46
    iz
    1.38
    ний
    1.34
    шы
    1.27
    ку
    1.26
    પ
    1.26
     وعلى
    1.20
    ционе
    1.20
    ésre
    1.18
    য়
    1.16
    Activations Density 0.045%

    No Known Activations