© 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. 60109
    Prev
    Next
    INDEX
    Explanations

    proposed or anticipated

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

    "Problem", "Executive Summary", "Business Problem", "Maximum Length"

    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
     Tax
    0.45
    貢
    0.42
    सन
    0.41
    थरूम
    0.41
     moo
    0.41
    zze
    0.40
     Newspaper
    0.40
     địa
    0.40
     mỹ
    0.39
     Bazaar
    0.39
    POSITIVE LOGITS
     ausgesch
    0.60
     ﺍ
    0.54
    ANGE
    0.53
     ಮಂಗಳ
    0.52
     цикл
    0.52
    START
    0.51
     Прави
    0.51
     Erweiter
    0.51
    fläche
    0.50
    PLEMENT
    0.50
    Activations Density 0.000%

    No Known Activations