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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14511
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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_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
     listeners
    1.16
    파일
    1.11
    Boards
    1.09
     boards
    1.08
     listening
    1.08
    聽
    1.08
    ⣀
    1.07
    <eos>
    1.07
    쯤
    1.06
     غور
    1.05
    POSITIVE LOGITS
    methoxy
    1.54
    inducing
    1.38
    thru
    1.37
    ී
    1.35
    กฎ
    1.32
    symbol
    1.31
     рады
    1.30
    ordin
    1.29
    послед
    1.29
    pell
    1.29
    Activations Density 0.010%

    No Known Activations