© 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. 47863
    Prev
    Next
    INDEX
    Explanations

    privacy policy discussions

    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
     Resume
    0.48
     Inn
    0.47
     /
    0.45
    ine
    0.45
     Intern
    0.43
     Dap
    0.43
     inn
    0.43
    daw
    0.43
     Genuine
    0.42
     jed
    0.42
    POSITIVE LOGITS
    ρα
    0.60
    ক
    0.54
    𝘤
    0.54
    講的是
    0.52
    隐私
    0.50
    м
    0.49
    Players
    0.49
    ли
    0.49
    у
    0.49
     बीटल
    0.49
    Activations Density 0.003%

    No Known Activations