© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35759
    Prev
    Next
    INDEX
    Explanations

    words starting with Sen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    0.52
    smittel
    0.47
    áne
    0.47
    sighted
    0.46
    見
    0.44
    lim
    0.43
    stitution
    0.43
     disposit
    0.43
    ishman
    0.43
    sc
    0.42
    POSITIVE LOGITS
     Sens
    0.50
    Sens
    0.47
     ayat
    0.47
     perm
    0.47
     as
    0.47
     comis
    0.46
     volna
    0.46
    ’
    0.46
     diffé
    0.46
     efect
    0.45
    Activations Density 0.015%

    No Known Activations