© 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. 55620
    Prev
    Next
    INDEX
    Explanations

    measurement categories and place identifiers

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

    technical terms and abbreviations

    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
     amyloid
    0.52
     classifications
    0.46
     trajectory
    0.46
     excursions
    0.45
     traumas
    0.44
     intrusions
    0.44
     blanks
    0.44
    暇
    0.44
    ing
    0.43
     tumour
    0.43
    POSITIVE LOGITS
     វា
    0.58
     Для
    0.55
     ഭക്ഷണം
    0.54
     Ла
    0.51
     ব্রহ
    0.51
     পিছনে
    0.50
     Semoga
    0.50
     Даже
    0.50
     পেছনে
    0.49
    모델
    0.49
    Activations Density 0.000%

    No Known Activations