© 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. 64225
    Prev
    Next
    INDEX
    Explanations

    finding yourself or something

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

    introducing specific points

    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
     chłop
    0.50
     Συν
    0.50
     მაგრამ
    0.49
     薄
    0.49
    န်
    0.48
    ხედ
    0.47
    ästä
    0.47
    ﻮ
    0.47
    드가
    0.47
    Ę
    0.45
    POSITIVE LOGITS
    as
    0.55
    uell
    0.46
    comers
    0.44
    asel
    0.43
    fas
    0.43
     aboriginal
    0.42
    es
    0.42
    cards
    0.42
    aways
    0.42
    quarters
    0.42
    Activations Density 0.000%

    No Known Activations