© 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. 160313
    Prev
    Next
    INDEX
    Explanations

    third decade

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

    locations, transport, or transitions

    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
     گوئ
    0.50
     puntual
    0.48
     گوئی
    0.47
     полез
    0.46
    ++)//
    0.46
     hủy
    0.46
     могло
    0.45
     হয়তো
    0.44
     verily
    0.44
     হয়ত
    0.43
    POSITIVE LOGITS
    Waves
    0.50
    -
    0.50
     SPACE
    0.48
     almonds
    0.47
    ropo
    0.47
    路的
    0.46
     cultures
    0.46
    瘁
    0.46
     Waves
    0.46
    大脑
    0.46
    Activations Density 0.001%

    No Known Activations