© 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. 19419
    Prev
    Next
    INDEX
    Explanations

    double

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

    double

    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
     as
    0.64
     a
    0.61
    FROM
    0.57
     chủ
    0.56
    ک
    0.55
     were
    0.55
    ocuk
    0.55
     établir
    0.54
     أس
    0.54
    IVING
    0.54
    POSITIVE LOGITS
     Double
    1.34
     double
    1.30
    Double
    1.16
     डबल
    1.14
     doble
    1.09
    双
    1.09
    double
    1.05
     duplo
    1.04
     doppia
    1.02
     двой
    0.99
    Activations Density 0.062%

    No Known Activations