© 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. 216539
    Prev
    Next
    INDEX
    Explanations

    action phrases and descriptors

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

    about pretty much anything

    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
    Config
    0.50
    conf
    0.50
    ckså
    0.49
    Client
    0.49
    Reserved
    0.48
    DAAR
    0.47
    ņ
    0.45
     Realt
    0.45
    ns
    0.45
    GROUP
    0.45
    POSITIVE LOGITS
    にお
    0.54
     anunci
    0.50
     everywhere
    0.50
     estavam
    0.49
    opedic
    0.49
     omnip
    0.48
     desen
    0.48
     endere
    0.48
     estaban
    0.48
    ﻠ
    0.47
    Activations Density 0.002%

    No Known Activations