© 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. 97670
    Prev
    Next
    INDEX
    Explanations

    customer protection, security

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

    largely valuable hybrids

    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
    龙
    0.51
     кандидат
    0.49
    询
    0.48
    园
    0.47
    Traversal
    0.46
    针
    0.46
    Funeral
    0.46
    ύ
    0.44
    ங்கல்
    0.44
    在该
    0.44
    POSITIVE LOGITS
     thei
    0.48
     veoma
    0.47
     vissa
    0.45
     utiliser
    0.45
     njegov
    0.45
     blijft
    0.44
     aflat
    0.43
     subsid
    0.42
     människ
    0.42
     lekker
    0.42
    Activations Density 0.002%

    No Known Activations