© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10574
    Prev
    Next
    INDEX
    Explanations

    what's on/going/in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Means
    0.41
    Solve
    0.41
    Ell
    0.39
     चाहें
    0.38
    \*
    0.38
    ش
    0.38
    警
    0.36
    *
    0.36
     одну
    0.36
    Means
    0.36
    POSITIVE LOGITS
     happening
    0.57
    setMaximum
    0.51
     yapıl
    0.49
     המ
    0.49
     علی
    0.49
    larını
    0.48
    avaju
    0.47
     mezi
    0.47
     nổi
    0.47
     অবশিষ্ট
    0.47
    Activations Density 0.127%

    No Known Activations