© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185753
    Prev
    Next
    INDEX
    Explanations

    crafts, tools, or economy

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

    proximity seeking, shared love

    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
    房间
    0.47
     Đ
    0.45
     Contrary
    0.44
     Vào
    0.43
    yty
    0.42
     Chiến
    0.42
     Phần
    0.42
     Hager
    0.42
     Marko
    0.41
     Comment
    0.41
    POSITIVE LOGITS
    鎮
    0.52
    媒體
    0.49
     utiliser
    0.48
     ounces
    0.47
    統領
    0.47
     médias
    0.47
    搖
    0.46
     биз
    0.46
    悳
    0.46
     ഇന്ത്യന്‍
    0.45
    Activations Density 0.000%

    No Known Activations