© 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. 240816
    Prev
    Next
    INDEX
    Explanations

    locations following "at"

    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
     Pest
    0.42
    遇到的
    0.41
    在线
    0.40
     Essex
    0.40
    ეს
    0.39
     Hour
    0.39
    乐
    0.39
     Enemy
    0.39
    粘贴
    0.39
    谘
    0.39
    POSITIVE LOGITS
    াজী
    0.46
     cominc
    0.46
    unati
    0.45
     buget
    0.45
    ATIV
    0.45
     добав
    0.44
    nesset
    0.44
     ajouté
    0.43
     aggiunto
    0.43
    െടുത്തു
    0.43
    Activations Density 0.003%

    No Known Activations