© 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. 12064
    Prev
    Next
    INDEX
    Explanations

    descriptive labels

    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
     subiect
    0.38
     اغ
    0.37
    ヒト
    0.36
     मेर
    0.36
    👤
    0.36
    HttpServlet
    0.36
    keyList
    0.35
    𝐖
    0.35
    SUBJECT
    0.35
     oportunidades
    0.34
    POSITIVE LOGITS
    更多
    0.46
     evolution
    0.44
    隠
    0.44
     full
    0.41
     generation
    0.41
     komplette
    0.40
     fuller
    0.40
     denaturation
    0.40
     Onc
    0.39
     amputation
    0.39
    Activations Density 0.000%

    No Known Activations