© 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. 163740
    Prev
    Next
    INDEX
    Explanations

    fool allnormal swapbuying afall so farcalculated My

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

    point to

    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
     and
    0.59
    ama
    0.55
     cuesta
    0.48
    city
    0.46
    pppp
    0.45
     dlr
    0.45
     g
    0.45
     city
    0.44
    shaped
    0.44
     kou
    0.44
    POSITIVE LOGITS
    RationalValue
    0.56
    พ์
    0.49
     случайно
    0.46
    મિક
    0.45
     dérivés
    0.45
     inconvén
    0.44
     одному
    0.43
    胫
    0.43
    ใน
    0.42
     succès
    0.42
    Activations Density 0.001%

    No Known Activations