© 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. 97593
    Prev
    Next
    INDEX
    Explanations

    non-english word identification

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

    legal technicalities vulnerabilities

    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
    PASS
    0.45
    ---
    0.45
    •
    0.44
    rare
    0.44
    Õ
    0.43
     ment
    0.43
     meu
    0.42
    -
    0.42
     my
    0.42
    instead
    0.42
    POSITIVE LOGITS
    大街
    0.51
     پروف
    0.51
     chợ
    0.51
     швид
    0.50
     달려
    0.48
     ሕ
    0.48
    𝙜
    0.47
     τρί
    0.47
     भोले
    0.46
     रोजी
    0.46
    Activations Density 0.000%

    No Known Activations