© 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. 107606
    Prev
    Next
    INDEX
    Explanations

    after all

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

    security updates and assessment

    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
    کی
    0.48
    粵
    0.48
     puro
    0.47
    സോ
    0.47
    chal
    0.46
     faciliter
    0.46
    جیت
    0.46
     moż
    0.45
    முக
    0.45
     ár
    0.45
    POSITIVE LOGITS
     ..."
    0.44
    verkehr
    0.43
     '}
    0.42
    iomanip
    0.41
     ...
    0.41
    ether
    0.40
    ungen
    0.40
    yticks
    0.40
    ignored
    0.40
    ener
    0.40
    Activations Density 0.000%

    No Known Activations