© 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. 193560
    Prev
    Next
    INDEX
    Explanations

    rooms than Jamaica

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

    origin and development

    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
    如何
    0.59
    я
    0.52
    Kết
    0.50
    :.
    0.49
    结论
    0.48
     Ста
    0.48
     efficient
    0.47
    在
    0.47
    пиа
    0.47
     результа
    0.46
    POSITIVE LOGITS
     UNESCO
    0.52
    zechos
    0.49
     commemoration
    0.48
     prépuce
    0.48
     visiter
    0.48
    atedral
    0.45
     寝
    0.45
    ktionen
    0.44
    ameras
    0.44
     trener
    0.44
    Activations Density 0.000%

    No Known Activations