© 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. 165648
    Prev
    Next
    INDEX
    Explanations

    cost effectively

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

    inflation takes

    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
    浈
    0.62
     सिंग
    0.54
     इट
    0.54
     दिश
    0.51
    ğun
    0.51
     Filho
    0.49
    یا
    0.48
     दुसरे
    0.48
     Primero
    0.48
     Акы
    0.48
    POSITIVE LOGITS
     φ
    0.49
     scatter
    0.47
    object
    0.46
    scoped
    0.44
    presentation
    0.44
    ج
    0.44
    ג
    0.44
    csp
    0.43
     diffuse
    0.43
     sauté
    0.43
    Activations Density 0.000%

    No Known Activations