© 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. 236418
    Prev
    Next
    INDEX
    Explanations

    automatic molding, communication by, skulls are, work, traffic, population

    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
    А
    0.56
    Ал
    0.52
    Т
    0.52
    ה
    0.51
    Ao
    0.50
    Произ
    0.50
    То
    0.49
    บริษัท
    0.49
    Sono
    0.48
    Đối
    0.48
    POSITIVE LOGITS
    梗
    0.47
     అలాగే
    0.46
    iletto
    0.45
    也会
    0.44
     उर्फी
    0.43
     كمان
    0.43
    也會
    0.43
     tiež
    0.41
     日
    0.41
     더욱
    0.41
    Activations Density 0.002%

    No Known Activations