© 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. 34-GEMMASCOPE-RES-131K
    7. 58156
    Prev
    Next
    INDEX
    Explanations

    names before `(priest)` or `(rugby league)`

    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
     dainty
    -0.76
     discernible
    -0.76
     those
    -0.75
     booked
    -0.75
     this
    -0.75
     Disinfect
    -0.75
    פיק
    -0.73
     premed
    -0.72
     ولا
    -0.72
     Prerequisite
    -0.70
    POSITIVE LOGITS
    SuspendLayout
    1.21
    1.16
    ResumeLayout
    1.09
    "/>
    1.00
    ByteString
    0.99
    )].
    0.98
     criterios
    0.92
    AKERS
    0.91
     клиентов
    0.90
    </thead>
    0.90
    Activations Density 0.001%

    No Known Activations