© 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. 53785
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

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

    AI future value

    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
    →
    0.49
    ω
    0.48
    boss
    0.48
     Bos
    0.47
    sn
    0.47
    就
    0.46
    Boss
    0.46
    sche
    0.44
    $$
    0.44
    kr
    0.44
    POSITIVE LOGITS
     extrémité
    0.59
     lateribus
    0.57
     alegria
    0.57
     vaisse
    0.56
     achat
    0.56
     caixa
    0.56
     válv
    0.55
     portada
    0.55
     propiedad
    0.54
     Антон
    0.54
    Activations Density 0.000%

    No Known Activations