© 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. 96156
    Prev
    Next
    INDEX
    Explanations

    double purchase

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

    dual or 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
    applicants
    0.55
    LookAnd
    0.54
    ശാല
    0.54
     言っ
    0.54
    ELIG
    0.54
    ჲ
    0.53
    রক্ষ
    0.52
     `>=`,
    0.52
     იაპ
    0.52
    imgInit
    0.50
    POSITIVE LOGITS
    s
    0.56
     spares
    0.52
     strips
    0.49
     double
    0.49
     Double
    0.47
    t
    0.46
     sails
    0.45
     finesse
    0.44
     fines
    0.43
     doubles
    0.43
    Activations Density 0.000%

    No Known Activations