© 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. 222109
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    port, labels, easy, accessible

    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
     According
    0.47
    rawd
    0.45
    हत्या
    0.44
     whose
    0.43
    हिट
    0.43
     உலகில்
    0.43
    whose
    0.43
    㝢
    0.43
    करने
    0.42
     உலக
    0.42
    POSITIVE LOGITS
     Kollegen
    0.49
     আমাকে
    0.46
    简洁
    0.46
     begrü
    0.46
    组件
    0.43
    麻烦
    0.43
    陆续
    0.43
     мои
    0.42
    负担
    0.42
     χρώ
    0.42
    Activations Density 0.001%

    No Known Activations