© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4185
    Prev
    Next
    INDEX
    Explanations

    depends on subjective factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    ocado
    1.40
    arsis
    1.19
    ucing
    1.15
    дав
    1.15
    romes
    1.14
     Themes
    1.12
     ucap
    1.12
    %]
    1.10
    rome
    1.09
     Palmas
    1.09
    POSITIVE LOGITS
    DIV
    1.08
     DIV
    1.04
    ynchronously
    1.03
     Div
    1.01
     Inver
    0.99
     Fulton
    0.95
    div
    0.94
    ージャー
    0.93
    Sund
    0.92
    educ
    0.92
    Activations Density 0.087%

    No Known Activations