© 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. 35352
    Prev
    Next
    INDEX
    Explanations

    no guarantee or assurance

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

    does not know

    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
     세상
    0.38
     tweaking
    0.38
     tweak
    0.38
     ~
    0.37
     gand
    0.37
     합성
    0.37
     détach
    0.37
     ร
    0.37
     zucch
    0.35
     stejně
    0.35
    POSITIVE LOGITS
    વેશ
    0.47
     desempenho
    0.44
     licenciado
    0.42
     assemblage
    0.41
    uento
    0.41
    éreo
    0.41
    soaked
    0.40
    fitrión
    0.40
    ilingual
    0.39
     assembled
    0.39
    Activations Density 0.000%

    No Known Activations