© 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. 12417
    Prev
    Next
    INDEX
    Explanations

    attacks or demeans hate speech

    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
    using
    1.21
    unched
    1.15
    一位
    1.08
    ately
    1.07
    汛
    1.07
    uldig
    1.06
    碁
    1.04
    oted
    1.03
    명
    1.03
    osts
    1.03
    POSITIVE LOGITS
     cabelos
    1.51
     множество
    1.49
     harmonies
    1.49
     guitar
    1.44
     tě
    1.40
     deliciously
    1.38
     cabelo
    1.38
     maravilh
    1.37
     vibes
    1.37
     aventuras
    1.34
    Activations Density 0.000%

    No Known Activations