© 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. 80877
    Prev
    Next
    INDEX
    Explanations

    visual attention

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

    removal, strange, you, is

    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
    >\
    0.47
    \$
    0.46
    \%
    0.46
    MR
    0.45
     \$
    0.44
    %
    0.44
    MS
    0.44
    %,
    0.44
     pinion
    0.43
    EM
    0.43
    POSITIVE LOGITS
     هذا
    0.61
     لحظ
    0.59
     اليوم
    0.56
     carefree
    0.55
     Erlebnis
    0.55
     यूँ
    0.54
     această
    0.53
     এই
    0.52
     nostalg
    0.52
    زندگی
    0.52
    Activations Density 0.001%

    No Known Activations