© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130730
    Prev
    Next
    INDEX
    Explanations

    facts, matrix, time, reception, stop

    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_40_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
    evil
    0.41
     Render
    0.40
    ibaba
    0.38
    狸
    0.38
    лети
    0.38
    render
    0.38
     പറയുന്നു
    0.37
    悪
    0.37
     Rendering
    0.36
    書いて
    0.36
    POSITIVE LOGITS
     reception
    0.43
    Reception
    0.38
     recepción
    0.38
     млн
    0.38
    琬
    0.38
    手册
    0.38
    рама
    0.38
     Reception
    0.37
    Ftp
    0.37
     SSL
    0.37
    Activations Density 0.000%

    No Known Activations