© 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. 15160
    Prev
    Next
    INDEX
    Explanations

    corporate marketing announcements

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

    product descriptions and details

    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
    host
    0.56
    Host
    0.52
    是一个
    0.51
     في
    0.45
    IN
    0.44
    cult
    0.43
    Cult
    0.43
    я
    0.43
    lic
    0.42
    itz
    0.42
    POSITIVE LOGITS
     মদ
    0.46
    ेप
    0.43
    ೂರ್
    0.43
    คโน
    0.43
    垷
    0.43
    ১৪
    0.43
     lapangan
    0.42
     کشاور
    0.41
    癀
    0.41
    عنی
    0.41
    Activations Density 0.000%

    No Known Activations