© 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. 14244
    Prev
    Next
    INDEX
    Explanations

    defend, draw, fought, easier

    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
    𝒆
    2.60
    𝒂
    2.54
    𝒊
    2.41
    𝒐
    2.29
    𝒍
    2.23
    యు
    2.16
    𝒄
    2.15
    களை
    2.03
    sister
    2.02
    𝒖
    2.01
    POSITIVE LOGITS
    ist
    2.01
    しくは
    1.90
    aroos
    1.79
    ूक
    1.73
    </tr>
    1.70
    ulah
    1.62
    𝑢
    1.56
    ([]
    1.51
    istin
    1.48
    ust
    1.46
    Activations Density 0.000%

    No Known Activations