© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13161
    Prev
    Next
    INDEX
    Explanations

    foreign quantifiers and adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     которые
    0.79
     oraz
    0.79
     (=
    0.76
     which
    0.72
     които
    0.72
     மற்றும்
    0.71
     ซึ่ง
    0.71
     (‘
    0.68
     (“
    0.67
     ambayo
    0.66
    POSITIVE LOGITS
     a
    0.57
    0.56
     hilarious
    0.53
     yksi
    0.53
     an
    0.52
    ొక్క
    0.52
     একটা
    0.51
     crappy
    0.51
     hardcore
    0.50
     brutal
    0.49
    Activations Density 0.000%

    No Known Activations