© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82557
    Prev
    Next
    INDEX
    Explanations

    when followed by a relative clause

    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
    যুক্ত
    0.46
    すべての
    0.44
    म
    0.43
    GraphQL
    0.43
    า
    0.41
    гну
    0.40
    ف
    0.39
    ٿ
    0.39
    <0x19>
    0.39
    ся
    0.38
    POSITIVE LOGITS
     brag
    0.47
     VAT
    0.47
     dreams
    0.46
     VIP
    0.46
     Vat
    0.46
     ordered
    0.46
    adamente
    0.45
    cig
    0.45
     paralysis
    0.45
     ideal
    0.44
    Activations Density 0.002%

    No Known Activations