© 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. 185985
    Prev
    Next
    INDEX
    Explanations

    for example

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

    investigator information or challenge period

    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
    dengan
    0.56
    𝓌
    0.48
    advertising
    0.48
    ieri
    0.47
     retelling
    0.47
     मार्च
    0.46
    Manchester
    0.46
    elled
    0.45
    Leod
    0.45
    册
    0.45
    POSITIVE LOGITS
    ৯
    0.48
     адрес
    0.48
     সুর
    0.47
    ৯৫
    0.47
    0.46
    })
    0.45
    )")
    0.45
     सिल्
    0.44
     عرف
    0.44
    ")
    0.44
    Activations Density 0.002%

    No Known Activations