© 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. 3374
    Prev
    Next
    INDEX
    Explanations

    numbers and common words

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

    went for, col -, as :

    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
    浏览器
    0.38
     fb
    0.38
     skim
    0.37
    ²+
    0.37
    比例
    0.37
    老爷
    0.36
     terror
    0.36
     어머니
    0.36
    妈妈
    0.35
     Bo
    0.35
    POSITIVE LOGITS
    prene
    0.41
    kennt
    0.40
    acionales
    0.40
     circumfer
    0.40
     esemplare
    0.40
    swadian
    0.40
    ichern
    0.38
    diverse
    0.38
    )}]{
    0.38
    hoog
    0.38
    Activations Density 0.405%

    No Known Activations