© 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. 31563
    Prev
    Next
    INDEX
    Explanations

    video recorders and graphics

    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
     two
    -1.12
     by
    -1.09
     an
    -1.07
     supremely
    -1.05
     from
    -1.04
     for
    -1.04
     one
    -1.02
     extraordinarily
    -0.98
     tailored
    -0.96
     creates
    -0.94
    POSITIVE LOGITS
     ded
    1.05
     Herbs
    1.01
     MOU
    1.00
    隂
    0.98
     😊
    0.97
    蠵
    0.96
     ACCIDENT
    0.94
     absl
    0.94
    beeren
    0.94
    튿
    0.93
    Activations Density 0.001%

    No Known Activations