© 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. 150865
    Prev
    Next
    INDEX
    Explanations

    information, knowledge, storage

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

    reduces size or requirements

    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
    hesive
    0.48
     Институт
    0.48
     kontin
    0.47
     حالات
    0.46
    ра
    0.46
    ă
    0.46
     IOP
    0.45
     राठ
    0.45
    as
    0.43
    ische
    0.43
    POSITIVE LOGITS
     ہوا۔
    0.44
    を行い
    0.42
    সাধ
    0.41
    ర్థిక
    0.41
    Ways
    0.41
    WAYS
    0.41
    ர்களால்
    0.41
    つの
    0.39
    пря
    0.39
    ₿
    0.39
    Activations Density 0.001%

    No Known Activations