© 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. 172656
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    scientist smelling and tasting

    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
    ᱖
    0.48
     ७
    0.46
    THIS
    0.46
     コート
    0.45
    this
    0.45
     passwords
    0.45
     contraseña
    0.45
     cientos
    0.44
     confrontations
    0.44
     confrontation
    0.44
    POSITIVE LOGITS
     kaldığımız
    0.45
    ជាមួយនឹង
    0.43
     spes
    0.43
     ster
    0.41
     ټ
    0.41
    ทราบ
    0.41
    鏡
    0.41
    一些
    0.41
     madde
    0.40
    씀
    0.40
    Activations Density 0.001%

    No Known Activations