© 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. 133365
    Prev
    Next
    INDEX
    Explanations

    1 Tim 2:5

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

    help you

    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
    URLConnection
    0.45
    DeviceId
    0.41
    직
    0.41
    ظمة
    0.41
    誤差
    0.40
     校
    0.40
    ικοί
    0.40
     নিজেকে
    0.40
    데일리
    0.39
    ಂಡ
    0.39
    POSITIVE LOGITS
     Miramar
    0.57
    ่
    0.51
     Venezuel
    0.51
     agen
    0.51
     encontrar
    0.50
     pavement
    0.50
     ATV
    0.50
     autoestima
    0.50
    举报
    0.49
     ayant
    0.49
    Activations Density 0.000%

    No Known Activations