© 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. 34016
    Prev
    Next
    INDEX
    Explanations

    cgi scripts

    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
    achable
    0.38
    dets
    0.38
    且
    0.38
    DetailPage
    0.37
    ReadFile
    0.37
    慢性
    0.37
    зывает
    0.37
    Holds
    0.37
    elligent
    0.36
    েন্ড
    0.36
    POSITIVE LOGITS
     بط
    0.40
     Fee
    0.39
    стары
    0.39
     guai
    0.39
     scopes
    0.39
    በ
    0.39
     porttitor
    0.38
     Bin
    0.38
     pelos
    0.38
    𝙞
    0.38
    Activations Density 0.000%

    No Known Activations