© 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. 163315
    Prev
    Next
    INDEX
    Explanations

    noun + noun phrases

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

    concepts and calculations

    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
    रा
    0.46
    า
    0.46
     tár
    0.46
     săptăm
    0.46
    ག་
    0.46
    소스
    0.45
     писатель
    0.44
     metá
    0.42
     உருவாக்கு
    0.42
    其
    0.42
    POSITIVE LOGITS
     Overhead
    0.51
     Tung
    0.50
    rung
    0.50
     =)
    0.48
    SV
    0.47
    Over
    0.46
     &=&
    0.45
    Dw
    0.44
     braced
    0.44
    砓
    0.44
    Activations Density 0.000%

    No Known Activations