© 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. 132236
    Prev
    Next
    INDEX
    Explanations

    raillastdefault

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

    syntax and rules

    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
    фор
    0.59
    袂
    0.53
     форме
    0.52
    㡀
    0.51
     нее
    0.50
    𒄀
    0.49
    хин
    0.48
    .",[
    0.48
     соци
    0.47
     архіви
    0.47
    POSITIVE LOGITS
     =
    0.53
     in
    0.52
     equation
    0.52
     helping
    0.52
     behind
    0.51
     assisting
    0.51
     navigation
    0.50
     rapping
    0.49
     cinematic
    0.49
     command
    0.48
    Activations Density 0.000%

    No Known Activations