© 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. 52393
    Prev
    Next
    INDEX
    Explanations

    foreign language identification

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

    specifying details

    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
     ረ
    0.45
    usia
    0.45
    amilton
    0.42
    uchs
    0.42
    ushan
    0.41
    olactone
    0.41
     Herring
    0.41
    参数向量
    0.41
    codon
    0.40
     ބ
    0.40
    POSITIVE LOGITS
     zusätzlich
    0.51
    爱
    0.48
    巴
    0.47
     zudem
    0.45
    纪
    0.45
     artístico
    0.44
    朝
    0.44
    生産
    0.44
    尽可能
    0.43
    を目
    0.43
    Activations Density 0.000%

    No Known Activations