© 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. 124827
    Prev
    Next
    INDEX
    Explanations

    incendiary, prodigious, or arduous

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

    specific nouns

    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
    amme
    0.49
    óle
    0.49
    elé
    0.48
     নাস
    0.47
    玼
    0.47
    amers
    0.46
     inferiore
    0.45
    řed
    0.45
    elő
    0.44
    aremos
    0.44
    POSITIVE LOGITS
     incendi
    0.43
     prodigious
    0.41
     breathtaking
    0.40
     धोका
    0.40
     त्याचा
    0.40
     △
    0.40
    动物
    0.40
    中毒
    0.39
     arduous
    0.39
     anthropology
    0.39
    Activations Density 0.000%

    No Known Activations