© 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. 18643
    Prev
    Next
    INDEX
    Explanations

    season 7 or £7.99

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

    personal information

    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
     Yoshi
    0.47
     S
    0.46
     N
    0.46
     R
    0.44
    J
    0.43
    toni
    0.42
     T
    0.42
     Использу
    0.42
    N
    0.42
     K
    0.41
    POSITIVE LOGITS
     সুস্পষ্ট
    0.50
     সরাস
    0.47
     ferns
    0.47
    മാര്‍
    0.46
    윕
    0.44
    یش
    0.44
     deletions
    0.43
    ').':
    0.42
     wildflowers
    0.42
     soweit
    0.42
    Activations Density 0.000%

    No Known Activations