© 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. 184679
    Prev
    Next
    INDEX
    Explanations

    daily online faculty

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

    built systems

    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
    墘
    0.56
     родителей
    0.52
     देखील
    0.51
     અલગ
    0.51
     প্রথমেই
    0.51
     아버지
    0.49
     частина
    0.49
     економі
    0.49
     प्रीपेड
    0.49
    窰
    0.49
    POSITIVE LOGITS
    m
    0.58
    biotics
    0.47
     cod
    0.46
     revisit
    0.46
     comet
    0.45
    xsl
    0.45
    pseudo
    0.44
    a
    0.44
     novo
    0.43
     comprehens
    0.43
    Activations Density 0.001%

    No Known Activations