© 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. 25727
    Prev
    Next
    INDEX
    Explanations

    sandstone, referendum, flush toilet

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

    demands exceptional, reducing operational

    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
     nonuniform
    0.48
     surveillance
    0.47
     bruise
    0.46
     stopping
    0.46
    //
    0.46
     discontinued
    0.46
     boast
    0.45
     trauma
    0.44
     discontinu
    0.44
     law
    0.43
    POSITIVE LOGITS
     ព
    0.50
    城的
    0.48
     వివర
    0.47
     سنة
    0.47
    那一
    0.47
    URNIZOR
    0.47
     వరకు
    0.47
     సందర్భంగా
    0.47
    倜
    0.47
    ancen
    0.46
    Activations Density 0.000%

    No Known Activations