© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7827
    Prev
    Next
    INDEX
    Explanations

    old

    np_acts-logits-general · gemini-2.5-flash-lite

    oldest, older, outdated, ancient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    azoline
    0.38
     महाप
    0.35
    គ្
    0.33
    стан
    0.33
    possibleTypes
    0.32
    <unused30>
    0.32
    ᱴ
    0.32
    วัสดี
    0.31
    ipton
    0.31
    悗
    0.31
    POSITIVE LOGITS
     old
    4.88
    old
    4.25
     OLD
    4.25
    Old
    3.95
    旧
    3.84
     Old
    3.81
    OLD
    3.78
     القد
    3.78
     पुराने
    3.75
    เก่า
    3.73
    Activations Density 0.545%

    No Known Activations