© 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. 111655
    Prev
    Next
    INDEX
    Explanations

    filed May

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

    barely singlepartner Mexico

    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
     crucifix
    0.52
     anore
    0.51
     extrap
    0.50
    竺
    0.50
     เศ
    0.50
    airi
    0.50
     나오
    0.49
     alkohol
    0.49
     irresponsible
    0.48
     ឬ
    0.48
    POSITIVE LOGITS
    Sav
    0.50
    同時に
    0.45
    Nam
    0.44
    BITS
    0.44
    iters
    0.44
    Tanggal
    0.44
    VISIBLE
    0.44
    Paid
    0.44
    WE
    0.43
    transferases
    0.43
    Activations Density 0.000%

    No Known Activations