© 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. 90146
    Prev
    Next
    INDEX
    Explanations

    dumpster and recycling costs

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

    explaining idioms, jokes, and potential threats

    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
    analisi
    0.48
    y
    0.47
    ал
    0.46
    laz
    0.46
    az
    0.46
    spiral
    0.45
    fraud
    0.44
    er
    0.44
    this
    0.43
    。
    0.43
    POSITIVE LOGITS
     kitchenette
    0.48
     প্রত্যেকের
    0.46
     élabor
    0.45
     '+':
    0.45
     각
    0.44
     THEY
    0.44
     eyepiece
    0.43
     jeweil
    0.43
     WITH
    0.43
     nCmdShow
    0.43
    Activations Density 0.002%

    No Known Activations