© 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. 30989
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    programming class begin

    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
     center
    0.42
     Amount
    0.41
     During
    0.40
     CO
    0.40
    eer
    0.39
     स्वी
    0.38
     venting
    0.38
    e
    0.38
    tex
    0.38
    質量
    0.38
    POSITIVE LOGITS
     Veron
    0.46
     használ
    0.45
    داء
    0.43
     valamint
    0.43
     smak
    0.42
     basta
    0.42
    дьми
    0.42
     quinquina
    0.42
     akşam
    0.42
     bisogna
    0.42
    Activations Density 0.000%

    No Known Activations