© 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. 27528
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

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

    speed and limits

    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
    嵇
    0.51
    𝐩
    0.49
     সেই
    0.49
     வசன
    0.48
     имму
    0.47
     इम्यून
    0.47
    絫
    0.46
     immunological
    0.46
     евре
    0.46
     ইন্টার
    0.44
    POSITIVE LOGITS
    ↵
    0.51
     Craig
    0.43
     stands
    0.42
     presidential
    0.42
     crave
    0.42
     Cit
    0.42
     shopper
    0.41
     Bezos
    0.40
     Langley
    0.40
    becca
    0.40
    Activations Density 0.000%

    No Known Activations