© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    wants and preferences

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

    wants and preferences

    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
     usamos
    0.35
     yǔ
    0.34
     luminance
    0.34
     அமைச்ச
    0.33
     melakukannya
    0.33
    これも
    0.33
    の効果
    0.33
    콘
    0.33
     annot
    0.32
     المختلف
    0.32
    POSITIVE LOGITS
     want
    1.20
     muốn
    1.19
     wanting
    1.14
    want
    1.09
     ingin
    1.09
     Want
    1.07
    想要
    1.03
    Want
    1.03
    ต้องการ
    1.02
     хотите
    1.02
    Activations Density 0.613%

    No Known Activations