© 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. 10890
    Prev
    Next
    INDEX
    Explanations

    tide, siren, lottery, elections

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

    seed to reproduce results

    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
    人在
    0.45
    लेल्या
    0.44
    el
    0.43
     rumored
    0.43
    yang
    0.41
    ye
    0.41
     হোটেল
    0.41
     M
    0.40
     आगमन
    0.40
     வெப்பநிலை
    0.40
    POSITIVE LOGITS
     sozinho
    0.47
     possibilités
    0.44
     sozinha
    0.43
     interests
    0.42
     podamos
    0.42
     Ztg
    0.42
     explotación
    0.42
    интере
    0.41
    颏
    0.41
    زاز
    0.40
    Activations Density 0.002%

    No Known Activations