© 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. 168338
    Prev
    Next
    INDEX
    Explanations

    file identifier in code

    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
    hens
    0.43
     επο
    0.39
     CORPOR
    0.38
    자와
    0.38
    繭
    0.38
    媺
    0.38
    바로
    0.37
    츠
    0.37
     отказа
    0.37
     стру
    0.37
    POSITIVE LOGITS
     Horticulture
    0.36
     Recreation
    0.35
     Lifestyle
    0.34
     querc
    0.34
    NTech
    0.34
     realizando
    0.34
    pet
    0.34
    Planning
    0.34
     céré
    0.34
    AsUpIndicator
    0.34
    Activations Density 0.001%

    No Known Activations