© 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. 1559
    Prev
    Next
    INDEX
    Explanations

    nothing to do with

    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
    ق
    1.26
     afterward
    1.16
    䈉
    1.16
     indefinite
    1.13
     echoed
    1.13
    ",
    1.09
    ".
    1.09
    ی
    1.09
     overturned
    1.07
    K
    1.06
    POSITIVE LOGITS
    ă
    1.27
     hins
    1.12
     playas
    1.07
    ısı
    1.06
    lukan
    1.05
    لة
    1.05
     paga
    1.05
     jā
    1.04
    ıkl
    1.03
    לים
    1.02
    Activations Density 0.002%

    No Known Activations