© 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. 109502
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    While understandable

    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
     எனவும்
    0.43
     prefabricated
    0.43
    imine
    0.42
    im
    0.42
    kW
    0.42
     i
    0.41
     વખત
    0.41
    য়া
    0.41
     extent
    0.40
     সূ
    0.40
    POSITIVE LOGITS
     तारे
    0.46
    粗
    0.45
    ريض
    0.45
    不好
    0.44
    點
    0.43
     bát
    0.43
     mía
    0.43
     favorita
    0.43
     hábitos
    0.43
    点
    0.43
    Activations Density 0.002%

    No Known Activations