© 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. 33076
    Prev
    Next
    INDEX
    Explanations

    Dyson products or Clarkson beat

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

    Dyson, Spanx, Bryson

    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
    verts
    0.45
     नवे
    0.45
    asság
    0.44
    ኪ
    0.44
    肆章
    0.44
    हुआ
    0.44
    allenges
    0.43
    propan
    0.42
     मीटिंग
    0.42
     formalities
    0.42
    POSITIVE LOGITS
     Practitioner
    0.40
    XSSFSheet
    0.38
     Hl
    0.38
     goutte
    0.38
     Preserve
    0.37
     �
    0.37
     Rotor
    0.37
     Except
    0.37
     Browse
    0.37
    Predict
    0.37
    Activations Density 0.002%

    No Known Activations