© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138879
    Prev
    Next
    INDEX
    Explanations

    health and user information

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

    reading data snippets

    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
    ﺶ
    0.59
    ৩
    0.54
     beide
    0.53
     entrambe
    0.52
    ﻪ
    0.52
     almeno
    0.51
    ේ
    0.51
    ﻲ
    0.51
     rapidement
    0.49
    Observers
    0.48
    POSITIVE LOGITS
    fits
    0.49
    swiper
    0.47
    线下
    0.44
    經
    0.43
    了一些
    0.43
    defs
    0.43
    forter
    0.43
    burg
    0.42
     definitions
    0.42
     protector
    0.42
    Activations Density 0.000%

    No Known Activations