© 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. 201989
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific words

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

    foreign words and concepts

    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
    lán
    0.46
    .
    0.46
     প্রকল্পটি
    0.45
    iga
    0.43
    ettes
    0.43
    úc
    0.42
    itan
    0.42
    ín
    0.42
    intero
    0.41
    .'),
    0.41
    POSITIVE LOGITS
     zmiany
    0.45
     நிற
    0.44
    இர
    0.43
    顏色
    0.42
    兩
    0.40
     نی
    0.40
     DN
    0.40
     SIA
    0.40
     स्वाद
    0.39
     вку
    0.39
    Activations Density 0.000%

    No Known Activations