© 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. 169229
    Prev
    Next
    INDEX
    Explanations

    concepts, ideas, and specific terms

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

    building details

    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
    ವರೆ
    0.49
    брав
    0.48
     bigli
    0.48
     カー
    0.45
    garia
    0.43
    引き続き
    0.43
    
    0.43
    incar
    0.43
     લો
    0.42
     nessun
    0.42
    POSITIVE LOGITS
     Begriffe
    0.52
     kaleidos
    0.49
     Ihr
    0.48
     innovations
    0.47
    問
    0.47
    వచ్చు
    0.47
     Ideen
    0.46
     overkill
    0.46
     fråga
    0.45
     Folge
    0.45
    Activations Density 0.000%

    No Known Activations