© 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. 221709
    Prev
    Next
    INDEX
    Explanations

    select your or noun phrase

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

    specific items and their consequences

    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
     procé
    0.50
     Foam
    0.49
     pedibusque
    0.48
     endoscopic
    0.47
     ovog
    0.45
     nuovo
    0.45
    砼
    0.45
     progenitor
    0.45
     ইলেক্ট্রোলাই
    0.45
     curricular
    0.45
    POSITIVE LOGITS
    裁
    0.50
    Month
    0.48
    MONTH
    0.46
     rarely
    0.45
    信任
    0.44
    監査
    0.44
     reliably
    0.43
     MONTH
    0.43
    UNITED
    0.43
    傭
    0.43
    Activations Density 0.006%

    No Known Activations