© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13176
    Prev
    Next
    INDEX
    Explanations

    account verification, access, and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ೀ
    0.64
    ي
    0.63
     carinatis
    0.61
     হের
    0.61
     ран
    0.60
    يذ
    0.59
     ziemlich
    0.59
     бом
    0.59
    ీ
    0.58
    '$\
    0.57
    POSITIVE LOGITS
     Account
    1.40
     account
    1.34
    Account
    1.25
    account
    1.14
     Accounts
    1.11
     accounts
    1.04
    Accounts
    0.96
     اکاؤنٹ
    0.96
     comptes
    0.91
     akun
    0.89
    Activations Density 0.026%

    No Known Activations