© 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. 4496
    Prev
    Next
    INDEX
    Explanations

    rate of, rate that, progress

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

    automation, service, presentation, interest

    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
     멋
    0.39
    eler
    0.37
    one
    0.37
    Red
    0.36
    dat
    0.36
    ONE
    0.36
    💡
    0.36
    🔬
    0.36
    One
    0.35
    round
    0.35
    POSITIVE LOGITS
    その後
    0.45
     যতই
    0.45
     laquelle
    0.45
     kojem
    0.45
     continuando
    0.45
     welchem
    0.45
     continuer
    0.44
     ambayo
    0.43
     którego
    0.42
     bleibt
    0.42
    Activations Density 0.000%

    No Known Activations