© 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. 233875
    Prev
    Next
    INDEX
    Explanations

    planet of the apes

    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
    they
    0.48
    .
    0.48
    সম
    0.47
     they
    0.47
    нія
    0.45
    They
    0.44
     could
    0.43
    0.43
    í
    0.42
    υτό
    0.42
    POSITIVE LOGITS
    منى
    0.53
    बद्ध
    0.49
     ilma
    0.48
    MyHomePage
    0.47
     produk
    0.46
    churn
    0.45
    します
    0.44
     எடுத்துக்கா
    0.44
     يصبح
    0.44
    दायी
    0.44
    Activations Density 0.003%

    No Known Activations