© 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. 47303
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

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

    advice or action

    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
     antiga
    0.44
    agliari
    0.42
     férias
    0.41
     Dateien
    0.41
    áreas
    0.41
     Vergangenheit
    0.40
     লোহার
    0.40
    羨
    0.40
     dificuldades
    0.40
     multidiscipl
    0.39
    POSITIVE LOGITS
     skin
    0.47
     stains
    0.47
    浓度
    0.44
     Uses
    0.44
    }{
    0.44
     đậm
    0.43
     skór
    0.43
     coral
    0.42
    ତ୍
    0.42
     smell
    0.42
    Activations Density 0.000%

    No Known Activations