© 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. 110375
    Prev
    Next
    INDEX
    Explanations

    bags are, guardian and, learn the

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

    code definition and instructions

    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
     encir
    0.45
     perj
    0.45
     cani
    0.42
    슭
    0.41
     cinemas
    0.41
     constriction
    0.41
     cin
    0.40
     geographies
    0.40
     fraternity
    0.39
    DropdownBox
    0.38
    POSITIVE LOGITS
    ريع
    0.46
    应对
    0.45
    initialized
    0.44
    acceler
    0.44
    壱
    0.44
    during
    0.43
     severely
    0.42
    workshop
    0.42
     desperately
    0.42
    program
    0.42
    Activations Density 0.002%

    No Known Activations