© 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. 241658
    Prev
    Next
    INDEX
    Explanations

    best results

    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
    lasses
    0.43
    と呼ば
    0.38
     '|
    0.37
     राइ
    0.37
    ্র
    0.36
     নাকি
    0.36
     Baker
    0.35
    iał
    0.35
    াষ
    0.35
    :|
    0.35
    POSITIVE LOGITS
     minuten
    0.52
    ालत
    0.50
     அதிகரி
    0.47
     Vier
    0.47
     worsen
    0.46
     конструкция
    0.46
    та
    0.45
     이전
    0.45
     கூடு
    0.44
     инстру
    0.43
    Activations Density 0.001%

    No Known Activations