© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159142
    Prev
    Next
    INDEX
    Explanations

    products, templates, games, feminine

    np_acts-logits-general · gemini-2.5-flash-lite

    planning, melt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    cstring
    0.50
    regression
    0.49
    သင့်
    0.49
    reject
    0.48
    မြင်
    0.48
    扰
    0.47
     خير
    0.47
    rejected
    0.47
     inkább
    0.47
    𝐬
    0.47
    POSITIVE LOGITS
     I
    0.56
     JI
    0.53
     ता
    0.46
    IFIER
    0.44
    UTRAL
    0.44
    겠다
    0.43
     insecticide
    0.43
    ファ
    0.43
    INCLUDING
    0.43
     JES
    0.43
    Activations Density 0.000%

    No Known Activations