© 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. 71630
    Prev
    Next
    INDEX
    Explanations

    job and contracts

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

    minor, estates, debugging, waiting, likely

    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
    מית
    0.44
    䡇
    0.44
    菒
    0.42
     Traveler
    0.42
    ()->
    0.42
    LECTION
    0.42
    地产
    0.41
     ['./
    0.41
    ेबल
    0.41
    有一些
    0.41
    POSITIVE LOGITS
     milliseconds
    0.49
     ασ
    0.49
     sizes
    0.48
    XS
    0.47
     milliamperes
    0.47
     volts
    0.47
     }^{+}
    0.46
     غیر
    0.46
    ances
    0.46
     pores
    0.46
    Activations Density 0.001%

    No Known Activations