© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77407
    Prev
    Next
    INDEX
    Explanations

    engaged intook herevents thatscoped allocator

    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_34/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
    hskip
    -0.87
    etheless
    -0.85
    igenous
    -0.85
    ctar
    -0.84
    reuters
    -0.81
    inerario
    -0.80
    TTTT
    -0.80
    轵
    -0.79
    ϯ
    -0.79
     oír
    -0.79
    POSITIVE LOGITS
    oston
    0.88
     took
    0.88
     лов
    0.85
     dexterity
    0.84
     gerakan
    0.84
     veter
    0.83
     proficient
    0.81
    guchi
    0.79
     fidd
    0.79
     gestures
    0.79
    Activations Density 0.002%

    No Known Activations