© 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. 153926
    Prev
    Next
    INDEX
    Explanations

    is

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

    indicates importance or preparation

    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
    在
    0.59
    ,/
    0.53
    已被
    0.47
    早就
    0.47
    inx
    0.46
    ش
    0.46
    其他
    0.46
     目前
    0.45
    (-\
    0.45
    året
    0.45
    POSITIVE LOGITS
     acesta
    0.50
     cui
    0.50
     féidir
    0.49
    போது
    0.49
    RAEL
    0.48
     is
    0.48
     usted
    0.47
     decir
    0.46
    th
    0.46
    ంగ్
    0.46
    Activations Density 0.158%

    No Known Activations