© 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. 166267
    Prev
    Next
    INDEX
    Explanations

    legal liability or questions

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

    future directions

    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
     profondes
    0.52
    و
    0.52
    ورا
    0.52
    ول
    0.51
     mécanismes
    0.48
    遴
    0.48
     obtenu
    0.48
    دة
    0.47
     وليس
    0.47
     völl
    0.46
    POSITIVE LOGITS
    esimo
    0.47
     教え
    0.47
     Bharti
    0.46
     QVector
    0.46
    </footer>
    0.45
    es
    0.45
     you
    0.45
    াচার
    0.45
     BVHTree
    0.44
    CSharp
    0.44
    Activations Density 0.001%

    No Known Activations