© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2320
    Prev
    Next
    INDEX
    Explanations

    resorting to, focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maupun
    1.50
    それは
    1.38
     ataupun
    1.33
    𝕞
    1.31
    움
    1.31
     panahon
    1.30
     kecepatan
    1.30
     ocurrido
    1.28
     interesante
    1.28
     tampak
    1.26
    POSITIVE LOGITS
     fpr
    1.86
     به
    1.70
     solely
    1.69
     specifically
    1.65
     rigidly
    1.65
     with
    1.65
     on
    1.62
     directly
    1.60
     freely
    1.54
    <unused2157>
    1.53
    Activations Density 1.449%

    No Known Activations