© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36599
    Prev
    Next
    INDEX
    Explanations

    object detection

    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_40_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
     modulus
    0.42
    ൨
    0.42
    бна
    0.40
    ధ
    0.40
    ران
    0.40
    ᄆ
    0.39
    últ
    0.38
    ————————————————
    0.37
    یکیشن
    0.37
    たい
    0.37
    POSITIVE LOGITS
    雏
    0.39
     Fitch
    0.38
     poison
    0.36
     palmit
    0.36
     Thr
    0.35
     প্যার
    0.35
    isierte
    0.35
     Stereo
    0.35
     matters
    0.34
     Fisher
    0.34
    Activations Density 0.000%

    No Known Activations