© 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. 237341
    Prev
    Next
    INDEX
    Explanations

    different languages and scripts

    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
    หลัง
    0.50
    turkish
    0.50
    0.48
    {
    0.46
    치가
    0.45
    ानंतर
    0.45
    after
    0.44
    myp
    0.44
     після
    0.44
    0.43
    POSITIVE LOGITS
    ಎಸ್
    0.51
     velocidades
    0.46
     bestimmen
    0.46
    常规
    0.46
     reiniciar
    0.46
    㴌
    0.45
     primordial
    0.44
    混凝
    0.44
     discretized
    0.44
     divergent
    0.44
    Activations Density 0.002%

    No Known Activations