© 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. 131995
    Prev
    Next
    INDEX
    Explanations

    forced through, asking questions

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

    why questions and explanations

    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
    L
    0.51
    的一部分
    0.48
    Cue
    0.46
    niveau
    0.43
    U
    0.43
     dáng
    0.43
     età
    0.43
    R
    0.43
    Minus
    0.43
    Parm
    0.43
    POSITIVE LOGITS
     forças
    0.45
    <unused2231>
    0.45
     জানিতে
    0.44
    opolymer
    0.43
    opolymers
    0.43
     privados
    0.43
     izvor
    0.43
    เซล
    0.42
     bulunan
    0.42
     polymeric
    0.42
    Activations Density 0.001%

    No Known Activations