© 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. 151004
    Prev
    Next
    INDEX
    Explanations

    designated time

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

    squaring numbers, cities, bulge, prime

    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
    เที่ยว
    0.50
     exfol
    0.47
    鉚
    0.46
    abilité
    0.45
     Hygiene
    0.45
    หรือไม่
    0.45
     thức
    0.44
     stadium
    0.44
    bond
    0.44
    ;
    0.44
    POSITIVE LOGITS
     गुप्ता
    0.55
    ENER
    0.44
     erfolgreich
    0.43
     सम्पन्न
    0.43
    ﻜ
    0.43
     Пав
    0.42
     CAUSED
    0.42
    geschwindigkeit
    0.42
     bekommen
    0.41
    有一定的
    0.41
    Activations Density 0.000%

    No Known Activations