© 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. 53-GEMMASCOPE-2-RES-65K
    7. 4983
    Prev
    Next
    INDEX
    Explanations

    positive sentiment about groups

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

    Gemma creators Google DeepMind

    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_53_width_65k_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
    噱
    0.40
    話題
    0.39
     możli
    0.38
     असल्याची
    0.38
     escánd
    0.38
     اتفق
    0.38
    等人
    0.37
    풉
    0.37
    龇
    0.37
     सुर्खियों
    0.37
    POSITIVE LOGITS
     wonderful
    2.23
    wonderful
    1.92
     amazing
    1.87
    素晴らしい
    1.70
     maravilloso
    1.66
     lovely
    1.62
    amazing
    1.62
     marvelous
    1.61
     marvellous
    1.59
    Wonderful
    1.55
    Activations Density 0.294%

    No Known Activations