© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102935
    Prev
    Next
    INDEX
    Explanations

    walking distance

    np_acts-logits-general · gemini-2.5-flash-lite

    pantsing, spanking, sexual, explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     legisl
    0.48
     legislative
    0.47
     podnik
    0.45
     welcomes
    0.44
     oyn
    0.43
     đón
    0.42
    Ꮯ
    0.42
    飛行
    0.42
     istot
    0.42
    迎
    0.42
    POSITIVE LOGITS
    endis
    0.48
     다만
    0.47
    apparition
    0.46
    Elemental
    0.45
     সেক্ষেত্রে
    0.45
    으나
    0.44
    >;
    0.43
     然而
    0.43
     حتى
    0.43
    तुम
    0.42
    Activations Density 0.000%

    No Known Activations