© 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. 177813
    Prev
    Next
    INDEX
    Explanations

    creative nature, destiny, judged

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

    "which" or "interest"

    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
    _
    0.50
    ir
    0.49
    de
    0.48
    like
    0.47
    交换
    0.47
    bapt
    0.45
    ma
    0.45
    वर
    0.44
    modo
    0.44
    yto
    0.44
    POSITIVE LOGITS
     necessária
    0.55
    冕
    0.50
     ktorá
    0.48
     destinée
    0.46
     spéc
    0.45
     která
    0.45
     destinada
    0.45
     noastră
    0.45
    ቺ
    0.45
     permitirá
    0.45
    Activations Density 0.002%

    No Known Activations