© 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. 40879
    Prev
    Next
    INDEX
    Explanations

    taken strong

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

    built-in liner

    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
    ३
    0.61
    ৩
    0.59
    ೪
    0.57
    ۳
    0.57
    ৪
    0.55
    LARGE
    0.54
    keywords
    0.53
    3
    0.53
    4
    0.52
    ४
    0.52
    POSITIVE LOGITS
     革
    0.46
    året
    0.46
     xScale
    0.44
     ستر
    0.43
     سو
    0.43
     იმ
    0.43
    GetService
    0.43
    äck
    0.42
    azität
    0.42
     au
    0.42
    Activations Density 0.000%

    No Known Activations