© 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. 187891
    Prev
    Next
    INDEX
    Explanations

    launch everytime

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

    working while attending

    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
    operasi
    0.47
     Cedex
    0.47
     왜
    0.46
    their
    0.46
     ROLL
    0.46
     LIT
    0.45
     SEND
    0.45
    ev
    0.45
     Л
    0.44
     LIKE
    0.44
    POSITIVE LOGITS
     tkinter
    0.48
    Turkish
    0.46
     marginBottom
    0.45
     turkish
    0.45
     molecules
    0.43
     synthesizer
    0.42
    可能です
    0.42
     mysqli
    0.41
     moz
    0.41
    Ela
    0.41
    Activations Density 0.000%

    No Known Activations