© 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. 57781
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     verständ
    -0.87
    どれも
    -0.82
    アジ
    -0.76
    坞
    -0.76
     impotence
    -0.74
    ర్
    -0.73
     Adhe
    -0.73
     UIKit
    -0.73
    zte
    -0.72
     Commence
    -0.71
    POSITIVE LOGITS
     Songtext
    0.74
    rento
    0.73
    런
    0.72
    innen
    0.72
    ливо
    0.71
     Gibt
    0.71
     fahr
    0.70
     mengak
    0.70
    according
    0.68
    ченных
    0.68
    Activations Density 0.510%

    No Known Activations