© 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. 53-GEMMASCOPE-2-RES-262K
    7. 87185
    Prev
    Next
    INDEX
    Explanations

    loft or custom pattern

    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_53_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
    ected
    0.46
     Pich
    0.38
    ちら
    0.38
    㪇
    0.38
    વાલ
    0.37
    する必要
    0.35
     Deja
    0.35
     focus
    0.35
     Focus
    0.34
    蝰
    0.34
    POSITIVE LOGITS
     loft
    0.43
    ۆ
    0.41
    פן
    0.41
     Loft
    0.39
     LOFT
    0.39
    Traversal
    0.38
    |_{\
    0.37
     оказалось
    0.37
     inspe
    0.37
    রব
    0.37
    Activations Density 0.000%

    No Known Activations