© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    hita Street

    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
    rbuf
    1.19
    wpilibj
    1.07
    <unused961>
    1.04
    coeffs
    1.01
    <unused1726>
    0.98
    rinsim
    0.94
    亓
    0.94
    rctx
    0.93
     slto
    0.93
    <unused971>
    0.93
    POSITIVE LOGITS
     Theatre
    1.09
     Square
    1.02
    TM
    1.00
    Mart
    1.00
     League
    0.99
     Street
    0.98
     Valley
    0.98
     Mode
    0.97
     Way
    0.97
    Ma
    0.96
    Activations Density 1.700%

    No Known Activations