© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8240
    Prev
    Next
    INDEX
    Explanations

    D-names or specific prefixes/suffixes

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

    drape, dredge, deduction, dungeon

    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
    Ꮠ
    0.40
    leftrightarrow
    0.39
    ĺ
    0.38
     கிமு
    0.38
    芻
    0.37
     кисло
    0.36
    ην
    0.36
     glLight
    0.35
    StorageSync
    0.35
    猢
    0.35
    POSITIVE LOGITS
     Dhar
    2.36
     Daryl
    2.31
     Dante
    2.22
     Dharm
    2.19
     Daphne
    2.19
    鄧
    2.19
    邓
    2.17
     Dunk
    2.16
     Dend
    2.16
     Dundee
    2.14
    Activations Density 0.217%

    No Known Activations