© 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. 10-GEMMASCOPE-RES-131K
    7. 127731
    Prev
    Next
    INDEX
    Explanations

    drawing comparisons with like

    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_10/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
     is
    -2.08
     This
    -2.06
     Interestingly
    -1.75
     With
    -1.65
    ),
    -1.64
    ⸙
    -1.62
     Since
    -1.60
     Even
    -1.57
     If
    -1.56
    ."
    -1.54
    POSITIVE LOGITS
    ⛦
    2.05
    }
    1.99
     ataca
    1.82
     schuldig
    1.81
    卨
    1.80
    秶
    1.79
    𓁹
    1.75
     vê
    1.74
    镞
    1.70
     camada
    1.68
    Activations Density 0.022%

    No Known Activations