© 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. 63964
    Prev
    Next
    INDEX
    Explanations

    numbers followed by closing brackets

    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
     so
    -1.25
    おわりに
    -1.09
     truly
    -1.08
     very
    -1.04
     what
    -1.04
     these
    -0.96
    нял
    -0.96
     agricultores
    -0.93
    When
    -0.93
     enhance
    -0.92
    POSITIVE LOGITS
    ]
    1.41
    "]
    1.23
    )
    1.20
     dargestellt
    1.17
    <h2>
    1.11
    では
    1.00
    そして
    0.99
     dokonce
    0.98
    oluble
    0.98
     debacle
    0.98
    Activations Density 0.021%

    No Known Activations