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. 31142
    Prev
    Next
    INDEX
    Explanations

    tune in / out / into

    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
    ◸
    1.51
     électronique
    1.39
    öffentlich
    1.33
     efficacement
    1.32
    诿
    1.32
     mécanique
    1.31
     léger
    1.30
     accès
    1.30
     intérieure
    1.29
     colère
    1.29
    POSITIVE LOGITS
    ει
    1.41
    те
    1.30
    ı
    1.28
    nment
    1.25
    ू
    1.23
    ь
    1.21
    Possibly
    1.19
     sensitized
    1.13
    রে
    1.13
    WAYS
    1.12
    Activations Density 0.001%

    No Known Activations