© 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. 91499
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

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

    percentages and numbers

    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
    大于
    0.55
    辐
    0.49
     규모
    0.47
     ৫০০
    0.46
    数目
    0.46
    சில
    0.45
    钿
    0.45
     ডেলি
    0.44
    阈
    0.44
     đẩy
    0.44
    POSITIVE LOGITS
     relating
    0.42
    '
    0.42
     related
    0.40
     confounding
    0.40
     mengh
    0.40
    ecas
    0.39
    another
    0.38
     concep
    0.38
     conce
    0.37
     harte
    0.37
    Activations Density 0.000%

    No Known Activations