© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1170
    Prev
    Next
    INDEX
    Explanations

    specific tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     handlebars
    1.25
    "/"
    1.20
     traces
    1.19
    tries
    1.18
     diaries
    1.16
    ebug
    1.16
    pointer
    1.16
    ='
    1.16
     buckets
    1.15
    らし
    1.14
    POSITIVE LOGITS
    usepackage
    1.72
    rinsic
    1.58
    documentclass
    1.57
     endow
    1.40
     возникновения
    1.34
     CNRS
    1.33
     implicit
    1.28
    设立
    1.24
    νο
    1.24
     оконча
    1.22
    Activations Density 0.020%

    No Known Activations