© 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. 237240
    Prev
    Next
    INDEX
    Explanations

    occupations and tasks

    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
    وات
    0.59
    د
    0.55
    م
    0.53
    ر
    0.53
    ام
    0.52
    و
    0.51
    ن
    0.51
     Shock
    0.49
     বলছি
    0.49
    u
    0.49
    POSITIVE LOGITS
     বিরাট
    0.53
     विरा
    0.50
     przeci
    0.50
    ită
    0.48
     научных
    0.48
     विज्ञान
    0.48
     ostatnich
    0.47
    ằm
    0.47
    '`
    0.47
     τε
    0.47
    Activations Density 0.000%

    No Known Activations