© 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. 182490
    Prev
    Next
    INDEX
    Explanations

    making connections

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

    asking for, substances and, world heritage

    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
     febrero
    0.50
    ظیم
    0.47
    летнего
    0.47
    मी
    0.46
     ブ
    0.46
    पं
    0.46
    рії
    0.45
    уго
    0.45
     년
    0.45
    یر
    0.44
    POSITIVE LOGITS
     APIDC
    0.48
    蘋
    0.47
    កាន់
    0.45
    etian
    0.43
     രണ്ട്
    0.43
    ವಿಲ್ಲ
    0.43
    udp
    0.43
    yap
    0.42
    穿越
    0.42
    絕對
    0.41
    Activations Density 0.000%

    No Known Activations