© 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. 240987
    Prev
    Next
    INDEX
    Explanations

    other mums, use, net, tipped to, continue to, distinction with, risk assessment

    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
    i
    0.50
    a
    0.50
    calorie
    0.48
    rapid
    0.48
    cea
    0.47
     туристи
    0.47
    z
    0.46
    ua
    0.44
    bnb
    0.44
    emin
    0.44
    POSITIVE LOGITS
     עם
    0.46
    所で
    0.43
    Что
    0.42
    این
    0.42
     UserController
    0.42
     BLUE
    0.42
    فر
    0.41
    ერს
    0.41
    ູບ
    0.41
    తారు
    0.41
    Activations Density 0.000%

    No Known Activations