© 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. 212802
    Prev
    Next
    INDEX
    Explanations

    a special

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

    identity and problematic content

    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
     sept
    0.50
    informat
    0.47
    是
    0.46
    2
    0.46
    不是
    0.45
    USING
    0.44
     или
    0.43
    8
    0.43
    ఐ
    0.43
     vérifier
    0.43
    POSITIVE LOGITS
     Moraes
    0.53
     Wallace
    0.52
    ávez
    0.51
     Melihat
    0.50
     Tomás
    0.50
     Lalu
    0.50
     Joao
    0.49
     Sunglasses
    0.49
     Olha
    0.49
    骅
    0.48
    Activations Density 0.000%

    No Known Activations