© 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. 98741
    Prev
    Next
    INDEX
    Explanations

    price and quality

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

    greeting, Chinese, second, India, fact

    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
    чув
    0.50
    mest
    0.50
    responsible
    0.49
    м
    0.49
    smart
    0.48
    même
    0.47
    치
    0.46
    اکي
    0.46
    ventus
    0.45
    educational
    0.45
    POSITIVE LOGITS
     Habitat
    0.53
     setzt
    0.53
     Rhine
    0.52
     Stopping
    0.52
     BECAUSE
    0.51
     因為
    0.50
     柄
    0.50
     setzte
    0.50
    礪
    0.50
     MIME
    0.49
    Activations Density 0.001%

    No Known Activations