© 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. 203708
    Prev
    Next
    INDEX
    Explanations

    "special characters" or words

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

    plays on words and phrases

    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
    θη
    0.54
    ترین
    0.52
    ელი
    0.50
    给了
    0.49
    혔
    0.48
    estown
    0.47
    urst
    0.47
    کٹ
    0.47
    LT
    0.46
    िल्‍
    0.45
    POSITIVE LOGITS
     Vero
    0.51
     hydrophobic
    0.44
     Vim
    0.43
     absorb
    0.41
     visceral
    0.41
     متغير
    0.41
     protégé
    0.41
     =",
    0.41
     Natürlich
    0.41
    فى
    0.41
    Activations Density 0.000%

    No Known Activations