© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 717
    Prev
    Next
    INDEX
    Explanations

    system operations and status

    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
    પતિ
    1.88
    ене
    1.81
    IMENTO
    1.70
    𐰀
    1.68
     catalyzes
    1.67
    <unused719>
    1.63
    URU
    1.63
    ClrType
    1.63
    Ř
    1.60
    І
    1.58
    POSITIVE LOGITS
     add
    1.30
     mas
    1.27
     priv
    1.19
     local
    1.18
     equip
    1.11
    i
    1.09
     bit
    1.08
    y
    1.07
     extra
    1.05
     anti
    1.04
    Activations Density 0.099%

    No Known Activations