© 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. 71662
    Prev
    Next
    INDEX
    Explanations

    coined/shaped

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

    tokens following specific 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
     healthful
    0.49
    豁
    0.45
     maximized
    0.45
     optimale
    0.44
     échantillons
    0.43
     intercal
    0.42
     Maks
    0.42
     диапазо
    0.42
    人們
    0.41
     maximally
    0.41
    POSITIVE LOGITS
    era
    0.51
    eran
    0.48
     hago
    0.47
    ӗ
    0.46
    istock
    0.45
     Puritan
    0.45
    rie
    0.44
    akkhan
    0.44
     dejan
    0.44
    ҫ
    0.44
    Activations Density 0.004%

    No Known Activations