© 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. 22-GEMMASCOPE-RES-131K
    7. 33663
    Prev
    Next
    INDEX
    Explanations

    coordinates and dimensions

    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_22/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
     նաև
    -1.20
     também
    -1.04
    蝟
    -0.94
     also
    -0.94
     OPPORT
    -0.92
     kwar
    -0.92
     设计
    -0.90
     character
    -0.89
     家居
    -0.88
    Commenting
    -0.87
    POSITIVE LOGITS
     
    1.07
    了下
    1.05
     first
    0.94
    elementAt
    0.90
     atheists
    0.88
    を読
    0.85
    了两
    0.84
    insk
    0.83
    brä
    0.83
    paž
    0.82
    Activations Density 0.003%

    No Known Activations