© 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. 149313
    Prev
    Next
    INDEX
    Explanations

    loving words and names

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

    explaining why deviations, risks, and interactions

    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
     énorme
    0.53
    гер
    0.47
    ր
    0.46
    ।
    0.46
    ᑉ
    0.46
    ขึ้น
    0.45
     vít
    0.45
    申报
    0.45
    \%.
    0.44
    볍
    0.44
    POSITIVE LOGITS
    eden
    0.53
     सुगंध
    0.51
    haven
    0.50
     lover
    0.49
    resents
    0.47
    rosa
    0.47
     hydrangea
    0.46
     been
    0.46
    eti
    0.45
     loving
    0.45
    Activations Density 0.000%

    No Known Activations