© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73870
    Prev
    Next
    INDEX
    Explanations

    fictitious, dentils, Weizmann, SOUTHSIDE, Kore, flicker, ☰

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -5.38
    0
    -5.19
    Initially
    -5.09
    5
    -5.09
    There
    -5.09
     
    -4.94
    Since
    -4.81
    However
    -4.78
    With
    -4.78
    Although
    -4.72
    POSITIVE LOGITS
    🧌
    3.97
    ⟞
    3.83
    ৄ
    3.75
    髎
    3.61
    ѣмъ
    3.61
    sterious
    3.61
    畚
    3.56
    breviations
    3.52
    胧
    3.48
    ⟝
    3.48
    Activations Density 1.632%

    No Known Activations