© 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. 47833
    Prev
    Next
    INDEX
    Explanations

    computer, technical, and proper names

    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
    เปลี่ยนแปลง
    0.50
    ladi
    0.46
    └──
    0.44
     പുറ
    0.44
     af
    0.44
    í
    0.44
    cia
    0.43
     گئے
    0.43
    နယ်
    0.43
     gir
    0.43
    POSITIVE LOGITS
     empfohlen
    0.46
     istiyorum
    0.45
     acompañado
    0.39
    하십시오
    0.39
     Crimson
    0.39
    PLEX
    0.38
     हूं
    0.38
     recommending
    0.38
    <0x9A>
    0.37
     artifact
    0.37
    Activations Density 0.004%

    No Known Activations