© 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. 168496
    Prev
    Next
    INDEX
    Explanations

    executed action; industry; language; national park; stumbled upon

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

    AI powered systems

    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
     Something
    0.54
     येत
    0.52
    something
    0.50
     ?”
    0.50
    荸
    0.49
     दैन
    0.49
     Knowles
    0.48
     Safety
    0.48
    get
    0.47
    的安全
    0.47
    POSITIVE LOGITS
     batches
    0.53
    ampled
    0.49
     complexes
    0.48
    ８
    0.47
     phrases
    0.45
    ει
    0.44
     outbreaks
    0.44
    ルー
    0.43
    リーナ
    0.43
    ５
    0.43
    Activations Density 0.001%

    No Known Activations