© 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. 162704
    Prev
    Next
    INDEX
    Explanations

    common words and phrases

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

    dictionary of responses

    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
     productie
    0.62
    ερμαν
    0.56
    äder
    0.55
    درس
    0.54
    ورد
    0.53
    اس
    0.50
    ﺿ
    0.50
    یدر
    0.50
    نب
    0.49
    έρ
    0.48
    POSITIVE LOGITS
     minor
    0.46
     ties
    0.46
    minor
    0.46
    Encode
    0.46
     Common
    0.45
     (
    0.45
    most
    0.44
    Encoded
    0.44
    some
    0.44
     courses
    0.44
    Activations Density 0.000%

    No Known Activations