© 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. 212402
    Prev
    Next
    INDEX
    Explanations

    defend, indemnify

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

    telescope house

    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
    Issledovatel
    0.49
     ristor
    0.47
     menyiapkan
    0.46
     restoran
    0.46
    쾰
    0.46
     اہم
    0.45
    閪
    0.45
     hvilket
    0.44
    DUNLAND
    0.44
    姦
    0.43
    POSITIVE LOGITS
     Milky
    0.50
     or
    0.49
     Penguin
    0.49
    у
    0.49
     Oxford
    0.48
     (
    0.46
    and
    0.46
     Or
    0.46
    la
    0.46
     Py
    0.46
    Activations Density 0.000%

    No Known Activations