© 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. 406
    Prev
    Next
    INDEX
    Explanations

    has a

    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
    á
    1.55
    ال
    1.35
    to
    1.30
    นำ
    1.24
    ка
    1.22
    of
    1.19
    ž
    1.16
    ھ
    1.13
    ки
    1.13
     encompassing
    1.09
    POSITIVE LOGITS
    fors
    1.44
    ﺭ
    1.44
     tendencia
    1.34
     sido
    1.34
     chhoti
    1.30
    ┎
    1.30
    ations
    1.29
     возможность
    1.29
    itations
    1.27
    㚘
    1.27
    Activations Density 0.215%

    No Known Activations