© 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. 78992
    Prev
    Next
    INDEX
    Explanations

    explaining probability and meaning

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

    limits flexibility

    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
    ،
    0.48
     bedrijf
    0.46
    <0xB5>
    0.45
     Правда
    0.45
     اثنين
    0.44
     beschäftigt
    0.44
     ভাই
    0.43
     নিষ্ঠ
    0.43
     станции
    0.43
    ared
    0.43
    POSITIVE LOGITS
     formalin
    0.50
    𝘱
    0.49
    probability
    0.47
     osse
    0.47
    लिंग
    0.47
    कार्
    0.46
    न्व
    0.45
    ध
    0.45
    꺾
    0.45
    forcer
    0.45
    Activations Density 0.001%

    No Known Activations