© 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. 43545
    Prev
    Next
    INDEX
    Explanations

    dust products, puzzle fans, phone call

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

    peace, universe, sugar, music, pressure

    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
     voici
    0.46
     plaus
    0.46
     చెప్పారు
    0.44
    ื้อง
    0.43
     Computing
    0.42
    にっいて
    0.41
     suffit
    0.40
    蘚
    0.40
    nahi
    0.40
     cohé
    0.40
    POSITIVE LOGITS
    тя
    0.48
    years
    0.45
    system
    0.44
    string
    0.43
     años
    0.42
    buck
    0.42
    pressure
    0.42
    നാള
    0.41
     “
    0.40
    Grand
    0.40
    Activations Density 0.000%

    No Known Activations