© 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. 58561
    Prev
    Next
    INDEX
    Explanations

    foreign characters 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
    lara
    0.46
     trastornos
    0.46
     recuperación
    0.41
     récupération
    0.41
     차
    0.41
     போக்குவரத்து
    0.40
     traum
    0.40
     प्रसारण
    0.40
    Joseph
    0.40
     काग
    0.40
    POSITIVE LOGITS
    (!
    0.45
     Ubuy
    0.44
     ид
    0.43
     ближе
    0.43
    ᕋ
    0.43
    上来
    0.42
     неко
    0.42
     소개해
    0.42
    স্তাফ
    0.41
    ขึ้น
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.