© 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. 88873
    Prev
    Next
    INDEX
    Explanations

    foreign nationals, drummer, validity, GDPR

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

    foreign language words and symbols

    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
    naye
    0.47
    neu
    0.43
     stesse
    0.42
     penulis
    0.42
    datab
    0.42
    ريبي
    0.41
    =?,
    0.41
     administer
    0.41
     خب
    0.41
    renz
    0.40
    POSITIVE LOGITS
    法施行
    0.53
     любит
    0.49
     violent
    0.47
    ्ठा
    0.47
     गरिएको
    0.46
    毯
    0.46
     फर
    0.46
     подходит
    0.44
     Dragons
    0.44
     Вул
    0.44
    Activations Density 0.001%

    No Known Activations