© 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. 107434
    Prev
    Next
    INDEX
    Explanations

    SERVPRO services

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

    apophenia and pareidolia

    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
    аз
    0.49
    three
    0.46
    IMAGES
    0.46
    了我
    0.45
    aš
    0.44
    씹
    0.44
    速度
    0.44
     comunicado
    0.44
    我已经
    0.44
    金
    0.44
    POSITIVE LOGITS
     เหมาะ
    0.52
     keer
    0.48
     তাঁহার
    0.48
     về
    0.47
     সহিত
    0.47
     چاہئے
    0.47
     haught
    0.47
     místo
    0.46
     sewing
    0.46
     关于
    0.46
    Activations Density 0.001%

    No Known Activations