© 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. 69144
    Prev
    Next
    INDEX
    Explanations

    explaining reasons or comparisons

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

    sensitivity, connections, structure, calculation

    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
     and
    0.49
     e
    0.49
    ve
    0.48
     al
    0.47
    br
    0.47
     t
    0.45
     finance
    0.45
     o
    0.44
    tt
    0.43
    及
    0.43
    POSITIVE LOGITS
    เพราะ
    0.58
    क्योंकि
    0.55
     ዋና
    0.52
    avasena
    0.51
    קס
    0.50
    มาตรฐาน
    0.49
     deoarece
    0.48
    ระหว่าง
    0.47
     γιατί
    0.47
     때문이다
    0.47
    Activations Density 0.000%

    No Known Activations