© 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. 57084
    Prev
    Next
    INDEX
    Explanations

    names ending in ich/ol/ert/ard

    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
     pronounce
    -0.83
     Adding
    -0.77
     sixteen
    -0.77
     impieg
    -0.76
     doing
    -0.76
     shel
    -0.74
    วี
    -0.73
     expands
    -0.72
     trying
    -0.71
     sä
    -0.71
    POSITIVE LOGITS
    olas
    0.89
    ALLY
    0.81
    èle
    0.80
    ConnectionState
    0.79
    irten
    0.78
    olian
    0.77
    anin
    0.77
    MMdd
    0.76
    bbero
    0.76
    밍
    0.75
    Activations Density 0.044%

    No Known Activations