© 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. 46379
    Prev
    Next
    INDEX
    Explanations

    just

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

    technical terms and services

    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
     dönt
    0.47
     promozione
    0.46
     fondamentali
    0.45
    庁
    0.44
    oforte
    0.44
     esenciales
    0.43
    之旅
    0.43
     hukuk
    0.43
    ాలను
    0.42
     گی
    0.42
    POSITIVE LOGITS
     reason
    0.51
     பேசிய
    0.50
    ifferentiated
    0.47
     Brain
    0.46
     ~/.
    0.46
    ણ
    0.46
    вит
    0.45
     어린
    0.45
    ]);
    0.45
     Reason
    0.44
    Activations Density 0.000%

    No Known Activations