© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4472
    Prev
    Next
    INDEX
    Explanations

    compound words and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mechanisms
    0.99
     Mechanism
    0.93
     xấu
    0.85
    诱
    0.82
     botones
    0.81
     Interpreter
    0.79
     Trab
    0.79
     Sensitivity
    0.77
    ology
    0.77
     Suppression
    0.77
    POSITIVE LOGITS
     priced
    0.86
     mainstream
    0.85
    逪
    0.80
     consumers
    0.79
    ってい
    0.79
    istet
    0.78
     standalone
    0.78
    tier
    0.78
     semi
    0.77
    isee
    0.77
    Activations Density 0.212%

    No Known Activations