© 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. 91614
    Prev
    Next
    INDEX
    Explanations

    figure sum or episode

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

    defined terms and structure

    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
    ਲਾਂ
    0.46
     broader
    0.44
     পাকিস্তানীদের
    0.44
     পর্য
    0.43
     enfermos
    0.43
     pathophys
    0.43
     syndromes
    0.43
    ɻ
    0.43
    pdo
    0.42
     params
    0.42
    POSITIVE LOGITS
     складу
    0.52
     Vict
    0.46
     قوي
    0.45
     рівня
    0.44
     Vita
    0.43
    запа
    0.42
     Vikt
    0.42
    riften
    0.42
     Викто
    0.42
    št
    0.41
    Activations Density 0.000%

    No Known Activations