© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9384
    Prev
    Next
    INDEX
    Explanations

    code, mood, or focus labels

    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
    Negative Logits
     insect
    0.45
    ECO
    0.45
    盻
    0.45
     Walth
    0.45
     droplet
    0.44
    ophyllum
    0.43
    MOTION
    0.43
     emitting
    0.43
     reloc
    0.42
    JET
    0.42
    POSITIVE LOGITS
     எண்ண
    0.49
    ըն
    0.45
    ஞ்சம்
    0.41
    ꜱ
    0.41
     змі
    0.41
    ուն
    0.40
    իր
    0.40
    感到
    0.40
    वीय
    0.40
     pēc
    0.39
    Activations Density 0.001%

    No Known Activations