© 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. 84618
    Prev
    Next
    INDEX
    Explanations

    market

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

    how AI is programmed

    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
     Gravel
    0.50
     spreadsheet
    0.47
     spreadsheets
    0.46
     gravel
    0.45
    प्पू
    0.45
     rugged
    0.43
     swagger
    0.43
    )}=
    0.43
    )+"
    0.43
     roues
    0.43
    POSITIVE LOGITS
    lí
    0.52
    obatan
    0.46
    biter
    0.46
    கள்
    0.45
    kert
    0.45
    सीन
    0.44
    nova
    0.44
     गुरू
    0.44
     कब्जे
    0.43
    मित्रा
    0.43
    Activations Density 0.001%

    No Known Activations