© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57708
    Prev
    Next
    INDEX
    Explanations

    our experts

    np_acts-logits-general · gemini-2.5-flash-lite

    our Internal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    颅
    0.42
    广
    0.42
     upotre
    0.40
     anden
    0.39
     timeframe
    0.39
    犇
    0.39
    에
    0.38
    供应链
    0.38
     Saclay
    0.38
    𒐪
    0.38
    POSITIVE LOGITS
    experts
    0.50
     বিশেষজ্ঞদের
    0.49
    okar
    0.46
     specialists
    0.46
    amalla
    0.45
    ଟ
    0.45
    funny
    0.45
    inspector
    0.45
     spécialistes
    0.45
     Букмекеры
    0.44
    Activations Density 0.001%

    No Known Activations