© 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. 47276
    Prev
    Next
    INDEX
    Explanations

    occupancy taxes, joy over

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

    distinction or argument components

    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
     있어요
    0.49
     Баскетбол
    0.47
    겠지만
    0.46
    궜
    0.45
    땃
    0.45
     aplatis
    0.44
    ایل
    0.44
     온
    0.44
    스터
    0.44
     მნიშვნელ
    0.43
    POSITIVE LOGITS
     sleepless
    0.52
     costly
    0.48
     prid
    0.48
     festa
    0.45
     midnight
    0.45
     volt
    0.44
     storytelling
    0.43
    toare
    0.43
     clash
    0.43
     cevap
    0.43
    Activations Density 0.000%

    No Known Activations