© 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. 19464
    Prev
    Next
    INDEX
    Explanations

    these

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

    these and both

    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
     yksi
    0.40
     দেশটি
    0.40
     {}",
    0.40
     одним
    0.38
     এটি
    0.38
     নামটি
    0.37
    rologist
    0.37
    某
    0.36
     Mr
    0.36
    {}",
    0.36
    POSITIVE LOGITS
    これらの
    1.89
    这两个
    1.75
     these
    1.70
    these
    1.67
    这两
    1.65
    這些
    1.52
    这些
    1.51
    These
    1.49
     этих
    1.48
     दोनों
    1.44
    Activations Density 0.223%

    No Known Activations