© 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. 5891
    Prev
    Next
    INDEX
    Explanations

    . Principal Meridian

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

    contrasenya encriptada

    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
    糁
    0.36
    marshalN
    0.34
     Verpack
    0.34
    칡
    0.33
    داشت
    0.33
    VIDED
    0.32
    ेंटीना
    0.32
    钠
    0.32
    OLYBDENUM
    0.32
    CrL
    0.31
    POSITIVE LOGITS
     ,
    0.37
     Point
    0.36
     _
    0.35
     Function
    0.33
     time
    0.33
     In
    0.32
     ;
    0.32
     checking
    0.32
     repeatedly
    0.32
     visually
    0.32
    Activations Density 0.059%

    No Known Activations