© 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. 148462
    Prev
    Next
    INDEX
    Explanations

    after 'was' started

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

    potential harm

    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
    woods
    0.49
    ні
    0.47
    房间
    0.47
    ből
    0.46
     contend
    0.46
    Probability
    0.46
    kirk
    0.46
    坊
    0.45
    鄙
    0.45
    más
    0.44
    POSITIVE LOGITS
     それぞれ
    0.48
    を示す
    0.48
    sealed
    0.46
     있게
    0.46
    getahuan
    0.43
     rong
    0.43
     reliant
    0.43
    reliant
    0.43
     Bex
    0.42
     relied
    0.42
    Activations Density 0.000%

    No Known Activations