© 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. 93632
    Prev
    Next
    INDEX
    Explanations

    technical or non-english sequences

    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
    endige
    0.51
    aal
    0.47
    ingle
    0.46
     는
    0.46
    attle
    0.45
    ating
    0.45
    icals
    0.45
    ueling
    0.44
    giving
    0.44
    ablement
    0.44
    POSITIVE LOGITS
    alassem
    0.50
     يو
    0.46
     můžete
    0.45
    ות
    0.44
     أحمد
    0.43
    সুম
    0.42
     hexa
    0.42
    ссмо
    0.41
    ק
    0.41
     DISPLAYSURF
    0.40
    Activations Density 0.000%

    No Known Activations