© 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. 122670
    Prev
    Next
    INDEX
    Explanations

    internet searches and related topics

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

    edge labeled, finite set

    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
    亚
    0.49
    减
    0.45
    联
    0.44
    Ꮽ
    0.44
    美国
    0.43
     Former
    0.43
     активность
    0.43
    ologio
    0.42
    膻
    0.42
    为空
    0.42
    POSITIVE LOGITS
    ä
    0.50
     engineers
    0.47
     engineering
    0.46
    engineering
    0.45
    ün
    0.45
     engineer
    0.44
    polls
    0.44
    im
    0.44
     рекла
    0.43
    redund
    0.43
    Activations Density 0.002%

    No Known Activations