© 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. 99448
    Prev
    Next
    INDEX
    Explanations

    date and time ordinals

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

    across multiple, pursuit of

    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
    ביל
    0.49
     observa
    0.48
     alebo
    0.47
    或者
    0.46
     interpreta
    0.46
     couches
    0.45
     deftly
    0.45
    坵
    0.45
    หรือ
    0.45
    ，《
    0.45
    POSITIVE LOGITS
     ሁለት
    0.48
    adapter
    0.47
    invited
    0.45
     सरल
    0.45
     ሌሎች
    0.45
    expired
    0.44
     випадку
    0.44
    ed
    0.44
     ସ
    0.44
    ehr
    0.44
    Activations Density 0.000%

    No Known Activations