© 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. 209387
    Prev
    Next
    INDEX
    Explanations

    determine prevalence

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

    LsotSales examination

    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
     Ді
    0.50
     Sei
    0.49
     प्रमोशन
    0.47
    κι
    0.46
    𝐈
    0.46
     Ainda
    0.46
     Й
    0.46
    क्सीडेंट
    0.45
    ♀
    0.45
    卜
    0.45
    POSITIVE LOGITS
     examination
    0.50
    ifrån
    0.44
     pemeriksaan
    0.43
     examinations
    0.43
     món
    0.42
     or
    0.42
    nisse
    0.41
     ወይም
    0.41
    than
    0.40
     கல்விய
    0.40
    Activations Density 0.000%

    No Known Activations