© 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. 125499
    Prev
    Next
    INDEX
    Explanations

    list or file path

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

    offer, entry, platforms, resizing

    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
     wprowad
    0.53
     bias
    0.50
     impart
    0.50
     travaille
    0.49
     écl
    0.48
    дық
    0.48
     remem
    0.48
    ს
    0.47
     rester
    0.47
    αλλ
    0.46
    POSITIVE LOGITS
    isDirectory
    0.51
    isShow
    0.50
    playlists
    0.47
    listdir
    0.46
    listFiles
    0.46
    PlayerDataCache
    0.45
    listOf
    0.45
    をご確認
    0.45
    ofType
    0.44
    win
    0.43
    Activations Density 0.000%

    No Known Activations