© 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. 105455
    Prev
    Next
    INDEX
    Explanations

    live, which, the, giving, one, hours, fingers, want, option, CBD

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

    multi-lingual or measurement units

    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
     Skype
    0.48
    ләре
    0.45
    ской
    0.44
    esam
    0.44
    枷
    0.42
    ется
    0.40
    ाराम
    0.40
     کمان
    0.39
    ISK
    0.39
     entendre
    0.39
    POSITIVE LOGITS
     dro
    0.48
    athlete
    0.46
     atletas
    0.46
     tof
    0.46
     venc
    0.45
    dro
    0.45
     മാ
    0.44
    扆
    0.44
    ferences
    0.44
     शुरुआती
    0.44
    Activations Density 0.000%

    No Known Activations