© 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. 184391
    Prev
    Next
    INDEX
    Explanations

    project stone AVAILABLE

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

    file handling modes

    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
    DISK
    0.43
    Differences
    0.39
    Therefore
    0.38
    http
    0.37
    Whatever
    0.37
    pples
    0.37
    ɣ
    0.37
     ])
    0.36
     dlatego
    0.36
     genoemd
    0.36
    POSITIVE LOGITS
     abrigo
    0.59
     edificio
    0.53
     viajes
    0.53
     dormir
    0.52
     foams
    0.51
     Autón
    0.50
     विगत
    0.50
     itineraries
    0.49
     bienestar
    0.48
     escolar
    0.48
    Activations Density 0.000%

    No Known Activations