© 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. 83747
    Prev
    Next
    INDEX
    Explanations

    introducing examples or approximations

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

    example, say

    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
     কিছু
    0.48
     rhiz
    0.46
     Paryayvachi
    0.45
     muchos
    0.43
     significative
    0.42
    !:
    0.41
     barbaric
    0.41
     следует
    0.40
     detonation
    0.40
     queer
    0.40
    POSITIVE LOGITS
    5
    0.64
    6
    0.63
    3
    0.61
    4
    0.54
    8
    0.52
    also
    0.50
     ۱۵
    0.50
    2
    0.50
     també
    0.49
     ۶
    0.49
    Activations Density 0.064%

    No Known Activations