© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28273
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_40_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
    pts
    0.40
    str
    0.39
    pt
    0.39
    tted
    0.37
    _[
    0.36
    hr
    0.35
    bt
    0.35
    want
    0.35
    dent
    0.35
    po
    0.35
    POSITIVE LOGITS
    萵
    0.42
    丐
    0.41
     Prose
    0.39
     ontvangen
    0.39
    ຜ
    0.39
     ব্যায়াম
    0.38
     Receive
    0.38
     Büro
    0.38
     Engaging
    0.38
    蔚
    0.38
    Activations Density 0.012%

    No Known Activations