© 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. 11147
    Prev
    Next
    INDEX
    Explanations

    leave feeling, emerge destitute

    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
    fresh
    0.38
    gp
    0.37
    ட்டா
    0.37
    expired
    0.36
    ště
    0.35
    sem
    0.35
    r
    0.35
    worn
    0.35
    bg
    0.34
    lama
    0.34
    POSITIVE LOGITS
    每次
    0.40
    也
    0.38
     sellest
    0.35
    ાવી
    0.35
    出去
    0.35
    ον
    0.34
     каждом
    0.34
     ontological
    0.34
    ાવ
    0.33
    лке
    0.33
    Activations Density 0.003%

    No Known Activations