© 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. 179251
    Prev
    Next
    INDEX
    Explanations

    Change Direction, Security Council, confusion with, ye shall, tends not, weiler puppy

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

    handle case-insensitivity

    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
    стра
    0.50
    constructed
    0.47
    殓
    0.46
     поток
    0.46
    敒
    0.45
    tamb
    0.44
     nostru
    0.44
     سید
    0.44
    PlayerData
    0.44
    Publish
    0.43
    POSITIVE LOGITS
     estados
    0.45
     conlle
    0.42
    五
    0.42
     cinco
    0.42
     characters
    0.41
     Ellison
    0.41
     Blackstone
    0.41
     dresser
    0.41
     五
    0.41
     interchanges
    0.41
    Activations Density 0.000%

    No Known Activations