© 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. 138800
    Prev
    Next
    INDEX
    Explanations

    superb product essay limitations

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

    project goals and objectives

    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
    enfant
    0.50
    COMPILE
    0.46
    OPENJDK
    0.45
    鐢
    0.44
    FEB
    0.44
    ០០
    0.44
     dikenal
    0.44
    Compiled
    0.44
    habilit
    0.43
    ௦
    0.43
    POSITIVE LOGITS
     line
    0.47
     brick
    0.46
    0.46
     power
    0.44
     level
    0.43
     toets
    0.43
     आलो
    0.42
     AMC
    0.41
     palco
    0.41
     focus
    0.41
    Activations Density 0.002%

    No Known Activations