© 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. 128927
    Prev
    Next
    INDEX
    Explanations

    recurrence, calls, art, holes

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

    LinkedIn searches

    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
    мян
    0.46
     GoName
    0.46
     Städ
    0.45
     Sólo
    0.45
    棻
    0.44
    HNO
    0.42
     Srps
    0.42
    隂
    0.42
     Aujourd
    0.42
     Dokter
    0.42
    POSITIVE LOGITS
     সংগীত
    0.48
     সঙ্গীত
    0.47
    ray
    0.47
     ray
    0.46
     circumferential
    0.46
     repeated
    0.45
    ox
    0.45
     securities
    0.44
     emulsion
    0.44
     വകു
    0.44
    Activations Density 0.000%

    No Known Activations