© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59758
    Prev
    Next
    INDEX
    Explanations

    squeeze through a straw

    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_all/layer_41_width_262k_l0_big
    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
     distaste
    0.41
     ratings
    0.41
    Contours
    0.40
    ontal
    0.39
    ტერ
    0.38
     cuanto
    0.37
     가능한
    0.36
    장
    0.36
    ENDOR
    0.36
    Visited
    0.36
    POSITIVE LOGITS
     pekerja
    0.40
    fem
    0.40
     Recreational
    0.40
    菽
    0.37
     recreational
    0.36
    !"));
    0.36
    raise
    0.36
    तरीय
    0.36
    ienka
    0.36
    भीत
    0.35
    Activations Density 0.012%

    No Known Activations