© 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. 53545
    Prev
    Next
    INDEX
    Explanations

    software implementation

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

    ratio scale

    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
     in
    0.48
    in
    0.46
     horribly
    0.45
    &
    0.44
     stricken
    0.44
    不存在
    0.43
    ोषित
    0.43
    χα
    0.43
    不受
    0.42
     v
    0.41
    POSITIVE LOGITS
    Enlaces
    0.47
     Cómo
    0.45
    に向
    0.44
     органі
    0.44
    
    0.44
    യാണ്
    0.43
    Puedes
    0.43
     permettant
    0.42
     مختلفة
    0.41
    ouvoir
    0.41
    Activations Density 0.000%

    No Known Activations