© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34204
    Prev
    Next
    INDEX
    Explanations

    abdomen and core

    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_16_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
    ുകൾ
    0.64
    čių
    0.59
    ൻ
    0.57
    ձ
    0.55
     Erik
    0.53
    ėti
    0.53
    ڄ
    0.53
     eight
    0.52
    ല
    0.52
     अर्ज
    0.52
    POSITIVE LOGITS
     abdom
    0.74
    肚
    0.74
     abdominal
    0.70
     perut
    0.69
     torso
    0.68
    腹
    0.66
     abdomen
    0.65
     thoracique
    0.64
     tummy
    0.60
    ท้อง
    0.59
    Activations Density 0.027%

    No Known Activations