© 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. 42085
    Prev
    Next
    INDEX
    Explanations

    languages or technical terms

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

    technology officer questions

    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
     misery
    0.50
     gospel
    0.48
     │
    0.47
     antif
    0.46
     happening
    0.46
     phenomenon
    0.46
     events
    0.46
     paramount
    0.46
     دار
    0.45
    ;
    0.45
    POSITIVE LOGITS
    NOW
    0.46
     indiqu
    0.44
     χρησιμοποι
    0.43
    摔
    0.42
     utilizamos
    0.42
     falamos
    0.42
     ядра
    0.41
     Utilizamos
    0.41
    誐
    0.41
     inclui
    0.41
    Activations Density 0.000%

    No Known Activations