© 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. 20929
    Prev
    Next
    INDEX
    Explanations

    technologies, abuse, great, year

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

    lists and measurements

    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
     戸
    0.52
     showcased
    0.52
     proz
    0.50
     समृ
    0.49
     அப்படியே
    0.47
     demeanor
    0.47
     dod
    0.46
     hosted
    0.46
     lam
    0.46
     ie
    0.45
    POSITIVE LOGITS
    "
    0.51
    смо
    0.45
    rano
    0.44
    occa
    0.44
     взаимодействия
    0.44
    ścic
    0.43
    Angry
    0.43
    2
    0.42
    رمی
    0.42
    рад
    0.41
    Activations Density 0.001%

    No Known Activations