© 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. 232772
    Prev
    Next
    INDEX
    Explanations

    foreign language and special characters

    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
     //'
    0.62
    ıları
    0.51
     Continent
    0.49
     Transitions
    0.49
    ').
    0.49
    t
    0.48
     ''),
    0.47
     істо
    0.47
    amorph
    0.47
     assi
    0.46
    POSITIVE LOGITS
     milhões
    0.46
    ður
    0.43
    ños
    0.43
     Anzeige
    0.42
    ーパー
    0.42
     pedir
    0.42
    起動
    0.41
    ុម
    0.41
    驍
    0.41
    DIR
    0.40
    Activations Density 0.002%

    No Known Activations