© 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. 120405
    Prev
    Next
    INDEX
    Explanations

    report were, know how, tend to, stir the, Baby Sleep

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

    dark matter, bass, stirring, cell

    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
     diante
    0.51
    ере
    0.49
    䖝
    0.49
     пред
    0.48
    интере
    0.47
    ерез
    0.47
    ة
    0.47
     дево
    0.46
    empres
    0.46
     ев
    0.46
    POSITIVE LOGITS
    ኾ
    0.41
    th
    0.41
    olli
    0.41
     Position
    0.41
     randomness
    0.41
     rohkem
    0.41
    ol
    0.40
     Thursdays
    0.39
     ज़्यादा
    0.39
     tastings
    0.38
    Activations Density 0.001%

    No Known Activations