© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 48185
    Prev
    Next
    INDEX
    Explanations

    Russian technical terms

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

    following specific words

    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
     Inferno
    0.41
    ,’’
    0.40
    بيوتر
    0.39
     Scuola
    0.38
     Colours
    0.38
    Buongiorno
    0.38
     Monza
    0.37
    叐
    0.37
    ঃখ
    0.37
     Istituto
    0.37
    POSITIVE LOGITS
     ප්ර
    0.47
    Რ
    0.44
     だけ
    0.41
    的的
    0.41
    irst
    0.41
     त्याच्या
    0.39
     によって
    0.39
    Გ
    0.38
    allowing
    0.38
    Ყ
    0.37
    Activations Density 0.034%

    No Known Activations