© 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. 62851
    Prev
    Next
    INDEX
    Explanations

    supervisory visits

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

    `info()` method calls

    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
     percep
    0.48
     tied
    0.48
     تیس
    0.47
     recept
    0.46
     correl
    0.46
     tendered
    0.45
    𝐆
    0.45
     Ist
    0.44
     dotycz
    0.44
    popular
    0.44
    POSITIVE LOGITS
    Roi
    0.48
    姮
    0.45
    循环
    0.44
    Attrib
    0.44
    igkeiten
    0.43
    وسف
    0.43
    姒
    0.43
    Missing
    0.43
    में
    0.43
    掑
    0.42
    Activations Density 0.000%

    No Known Activations