© 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. 3080
    Prev
    Next
    INDEX
    Explanations

    words starting with Tal

    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
     siècles
    -0.73
    ショナル
    -0.73
     Next
    -0.73
     although
    -0.72
    IndexOutOfBounds
    -0.70
    ṟ
    -0.70
    ็ต
    -0.68
    seye
    -0.67
    zete
    -0.66
    Forte
    -0.66
    POSITIVE LOGITS
    Tal
    1.31
    ented
    1.27
     Tal
    1.16
    tal
    1.09
     tal
    1.05
     TAL
    1.02
    tale
    0.97
     tale
    0.96
    TAL
    0.96
     Tale
    0.96
    Activations Density 0.016%

    No Known Activations