© 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. 31-GEMMASCOPE-2-RES-262K
    7. 136649
    Prev
    Next
    INDEX
    Explanations

    voyeurism, abduction, objective description

    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_31_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
    {
    0.46
    Move
    0.45
    +
    0.45
    Ins
    0.45
    ires
    0.44
    Early
    0.43
    بعض
    0.43
    Over
    0.42
    Every
    0.42
    Flu
    0.42
    POSITIVE LOGITS
     scienze
    0.57
     visi
    0.57
     vutto
    0.52
     INCIDENTAL
    0.51
     ノ
    0.50
     имя
    0.50
     医学
    0.50
    科學
    0.48
     sciences
    0.46
     Jacobian
    0.46
    Activations Density 0.002%

    No Known Activations