© 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. 75184
    Prev
    Next
    INDEX
    Explanations

    SELECT, parks, Display

    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
    ough
    0.50
    리
    0.49
    织
    0.46
     shortstop
    0.45
    sounding
    0.45
    熒
    0.45
    记忆
    0.45
    ඪ
    0.44
    點
    0.44
    ும்பி
    0.43
    POSITIVE LOGITS
     اگر
    0.46
     člove
    0.46
     necesarios
    0.45
     Sumber
    0.42
    RES
    0.42
    Anagram
    0.42
     procurando
    0.41
     siguiendo
    0.41
     کدام
    0.41
     کاب
    0.40
    Activations Density 0.001%

    No Known Activations