© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 1401
    Prev
    Next
    INDEX
    Explanations

    being picky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     rent
    0.45
     wert
    0.45
    พ์
    0.45
     Does
    0.42
    ,
    0.41
    Rent
    0.41
     Einst
    0.41
     degr
    0.41
     rich
    0.40
     markt
    0.40
    POSITIVE LOGITS
    میان
    0.50
     깨
    0.48
    ິ
    0.48
    リューション
    0.48
     પોસ્ટ
    0.47
     آمر
    0.46
     تلیفون
    0.46
    cknowledg
    0.46
     ತಿ
    0.46
    ށ
    0.46
    Activations Density 0.000%

    No Known Activations