© 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. 208721
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and nouns

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

    without judgment

    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
    取り
    0.47
    その
    0.45
    ものは
    0.44
     dinding
    0.44
     phù
    0.43
    زندگی
    0.43
    時は
    0.43
    _(
    0.43
     autres
    0.43
     które
    0.42
    POSITIVE LOGITS
     फ्रे
    0.48
     Wix
    0.47
    kaa
    0.47
    kere
    0.47
    ablen
    0.46
     postdoc
    0.46
    ological
    0.45
     participated
    0.45
     репре
    0.45
     Божи
    0.45
    Activations Density 0.001%

    No Known Activations