© 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. 162591
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    let

    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
    ної
    0.50
    ні
    0.47
     bandeja
    0.46
    석
    0.46
    ٹھ
    0.45
    ज़
    0.45
    یز
    0.45
    所に
    0.44
    ĵ
    0.44
    їн
    0.44
    POSITIVE LOGITS
    Naturally
    0.46
    varying
    0.46
     новогод
    0.44
    ारीरिक
    0.44
     Weihnacht
    0.44
     Naturally
    0.43
     கூறப்படுகிறது
    0.43
    InputDir
    0.43
     különb
    0.42
     बिल्
    0.42
    Activations Density 0.000%

    No Known Activations