© 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. 38688
    Prev
    Next
    INDEX
    Explanations

    optional or conditional disclosures

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

    flow, house, stl, artist

    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
     eigenvectors
    0.52
     landed
    0.51
     apologized
    0.50
     reiterated
    0.49
     phénom
    0.48
     =-
    0.46
     downregulated
    0.46
     MW
    0.46
     phenomen
    0.45
     bothered
    0.45
    POSITIVE LOGITS
    簡単に
    0.48
    ﻼ
    0.48
    ent
    0.48
    examples
    0.47
    비
    0.46
    烏
    0.45
    乌
    0.44
    нями
    0.43
    无
    0.43
    ની
    0.42
    Activations Density 0.000%

    No Known Activations