© 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. 128745
    Prev
    Next
    INDEX
    Explanations

    referring to things

    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
    руса
    -1.05
    これらの
    -1.01
     malattie
    -1.00
    umán
    -1.00
    这些
    -0.98
    這些
    -0.97
     могла
    -0.96
     होगा
    -0.91
     ruinas
    -0.91
    和
    -0.90
    POSITIVE LOGITS
     Menschheit
    1.25
     in
    1.24
     voren
    1.02
    ૮
    1.02
    轳
    0.98
    íř
    0.97
     procedentes
    0.96
    emplares
    0.94
     tématu
    0.94
    ကိုးက
    0.91
    Activations Density 0.094%

    No Known Activations