© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81613
    Prev
    Next
    INDEX
    Explanations

    Q , agreed , Robust , Blue

    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
    Gore
    -0.83
    Shotgun
    -0.82
    Strut
    -0.81
     primeiras
    -0.76
     Gore
    -0.74
    Timetable
    -0.74
    Atra
    -0.74
    Serbia
    -0.73
     yelled
    -0.73
    手绘
    -0.73
    POSITIVE LOGITS
    erin
    0.84
    gallery
    0.83
     COMMITTEE
    0.81
    ENSE
    0.78
     committee
    0.77
    İZ
    0.77
     экза
    0.77
     просмотра
    0.77
    ਦਾ
    0.77
    ERS
    0.76
    Activations Density 0.000%

    No Known Activations