© 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. 193751
    Prev
    Next
    INDEX
    Explanations

    future built

    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
     WISE
    0.41
     sectional
    0.41
     Hate
    0.40
     hObject
    0.40
     trialComponents
    0.40
     फेस
    0.39
     Expensive
    0.38
     」
    0.38
     exclamation
    0.38
     Largest
    0.38
    POSITIVE LOGITS
    index
    0.39
    walker
    0.38
     constituye
    0.38
    institution
    0.37
     기관
    0.36
    assoc
    0.35
    ъм
    0.35
    стики
    0.35
    eine
    0.35
    zeum
    0.34
    Activations Density 0.002%

    No Known Activations