© 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. 33928
    Prev
    Next
    INDEX
    Explanations

    directive or Sinatra

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

    cough, lice, systems, itis

    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
     êtes
    0.59
     oublié
    0.54
     nėra
    0.52
     überall
    0.51
     occupé
    0.49
     épars
    0.49
     ụ
    0.49
     răz
    0.49
     expériment
    0.48
     există
    0.48
    POSITIVE LOGITS
     Directive
    0.49
     Sinatra
    0.47
    阻止
    0.46
    商务
    0.45
     કરીને
    0.44
    滤
    0.42
    穌
    0.42
    한다고
    0.42
    〢
    0.41
     directives
    0.40
    Activations Density 0.001%

    No Known Activations