© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4600
    Prev
    Next
    INDEX
    Explanations

    profoundly/deeply + negative adjective

    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
    is
    2.20
    ن
    1.94
    ли
    1.71
    are
    1.45
    id
    1.41
    و
    1.39
    ally
    1.34
    ion
    1.31
    هل
    1.30
    ie
    1.29
    POSITIVE LOGITS
    atthena
    1.56
    통산
    1.54
    acchati
    1.51
     niềm
    1.46
     errMsg
    1.43
    Aloe
    1.41
    ❤️❤️
    1.40
    邑
    1.40
    dür
    1.38
     profondément
    1.38
    Activations Density 0.235%

    No Known Activations