© 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. 187622
    Prev
    Next
    INDEX
    Explanations

    advisory vote

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

    IT Lab Support

    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
    لو
    0.56
    ة
    0.51
    分離
    0.49
    យ
    0.48
    LCD
    0.47
     روستا
    0.46
    Eo
    0.46
    نه
    0.46
    హి
    0.45
    ను
    0.45
    POSITIVE LOGITS
     principale
    0.46
     molyb
    0.44
     поперед
    0.44
     consigli
    0.43
     veroor
    0.43
    ാരോഗ്യ
    0.42
     principaux
    0.42
    assaytype
    0.42
    ｆ
    0.42
     pää
    0.41
    Activations Density 0.000%

    No Known Activations