© 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. 188786
    Prev
    Next
    INDEX
    Explanations

    copyright and copyright notices

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

    Oahu, easiest trip, offers

    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
    зі
    0.48
     смогут
    0.45
    Ꭾ
    0.45
     metabolites
    0.44
     바이
    0.44
     cytokines
    0.44
    ాలు
    0.43
    顕
    0.43
     لاءِ
    0.43
    다
    0.42
    POSITIVE LOGITS
    dsp
    0.54
    datal
    0.50
     alcun
    0.50
    firestore
    0.46
    brew
    0.46
     arrière
    0.45
    dataPath
    0.45
    carrito
    0.44
    cursor
    0.44
    paginate
    0.44
    Activations Density 0.001%

    No Known Activations