© 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. 225614
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     Crete
    0.46
     മ
    0.46
     İs
    0.45
     ভোক্ত
    0.43
    itudes
    0.43
    ność
    0.43
     своем
    0.42
     आफ्नो
    0.42
     ለ
    0.42
    endium
    0.42
    POSITIVE LOGITS
    орга
    0.44
     shuffled
    0.44
     collapsible
    0.44
     група
    0.44
     cycled
    0.43
     gruppi
    0.42
     FEST
    0.42
    双
    0.42
    冒
    0.42
    第一次
    0.41
    Activations Density 0.001%

    No Known Activations