© 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. 199673
    Prev
    Next
    INDEX
    Explanations

    vanity dresser, anniversary reunion

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

    list of numbers or gratification

    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
     pallets
    0.46
    isy
    0.45
    scre
    0.45
    ita
    0.45
    abler
    0.45
    inder
    0.44
    :
    0.43
     ଯ
    0.43
    resher
    0.43
    buttonclick
    0.42
    POSITIVE LOGITS
    פור
    0.52
    רג
    0.49
    פר
    0.49
    המ
    0.48
    各種
    0.47
    ר
    0.46
     Shad
    0.45
    ल्पन
    0.45
    訢
    0.45
     Members
    0.44
    Activations Density 0.001%

    No Known Activations