© 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. 62957
    Prev
    Next
    INDEX
    Explanations

    CA followed by numbers

    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
    ęt
    -0.75
     Jap
    -0.72
    ]!='
    -0.71
    dior
    -0.71
     pani
    -0.70
     Targ
    -0.70
     Trapp
    -0.70
     fission
    -0.69
     anarchy
    -0.69
     FORE
    -0.68
    POSITIVE LOGITS
     drowning
    0.75
    workflow
    0.74
     ending
    0.73
    Exhaust
    0.72
     refined
    0.71
    filterBy
    0.69
     Owens
    0.69
    ulli
    0.69
    侠
    0.68
    芳
    0.68
    Activations Density 0.056%

    No Known Activations