© 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. 59080
    Prev
    Next
    INDEX
    Explanations

    allegedly flying

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

    numbers and related words

    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
     “
    0.58
     (“
    0.57
    M
    0.55
     be
    0.53
     «
    0.53
     +,
    0.53
     l
    0.51
    -,
    0.50
     camer
    0.50
    T
    0.50
    POSITIVE LOGITS
    ogany
    0.51
    IsMethod
    0.49
     ovipares
    0.48
     الايه
    0.48
     divaricatis
    0.48
    <unused674>
    0.48
     الفصل
    0.47
    ipps
    0.47
     الگ
    0.47
    ärer
    0.46
    Activations Density 0.000%

    No Known Activations