© 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. 44256
    Prev
    Next
    INDEX
    Explanations

    would you mind

    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
    ка
    1.94
    ק
    1.64
    ین
    1.59
    ку
    1.54
     год
    1.49
    ط
    1.46
    ке
    1.45
    ти
    1.42
    SON
    1.42
    я
    1.41
    POSITIVE LOGITS
     sabbam
    1.63
    ます
    1.53
    yim
    1.50
     okay
    1.42
     worsen
    1.41
    と思います
    1.40
    اموش
    1.38
    ますが
    1.38
    なく
    1.37
    ythe
    1.36
    Activations Density 0.001%

    No Known Activations