© 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. 54757
    Prev
    Next
    INDEX
    Explanations

    Waist Factory, label, audios

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

    long time

    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
     hostages
    0.47
     nicknamed
    0.46
     bully
    0.45
     परेश
    0.44
     hostage
    0.44
    ї
    0.43
     kanggo
    0.43
     colloqu
    0.43
     ஹீரோ
    0.42
     nickname
    0.41
    POSITIVE LOGITS
    整个
    0.54
     它
    0.50
    Mutable
    0.47
    ovi
    0.46
    一系列
    0.46
    akaranam
    0.46
     McDonalds
    0.46
     ecosystems
    0.45
     Sedona
    0.44
     Urbana
    0.43
    Activations Density 0.000%

    No Known Activations