© 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. 249278
    Prev
    Next
    INDEX
    Explanations

    how and where questions

    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
     a
    0.32
    d
    0.32
     چنین
    0.28
     numerous
    0.25
     بیش
    0.25
    ʜ
    0.24
    a
    0.24
     discharged
    0.24
    这样的
    0.24
     многочис
    0.24
    POSITIVE LOGITS
     how
    0.44
     cómo
    0.39
     hvor
    0.37
    how
    0.37
     কিভাবে
    0.36
     hvordan
    0.33
    ك
    0.32
     where
    0.31
     waar
    0.31
     why
    0.31
    Activations Density 0.075%

    No Known Activations