© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66826
    Prev
    Next
    INDEX
    Explanations

    starts of phrases and names

    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
     Američ
    -1.18
    providedIn
    -1.16
     harap
    -1.15
     hunde
    -1.11
     silikon
    -1.09
     plakat
    -1.09
    CardHeader
    -1.09
     gangen
    -1.05
     triko
    -1.02
     kritik
    -1.02
    POSITIVE LOGITS
     hoang
    1.00
    k
    0.95
    Inves
    0.94
     among
    0.94
    Soma
    0.94
     dazu
    0.92
    ナル
    0.91
     options
    0.90
     asian
    0.90
    Importante
    0.90
    Activations Density 0.000%

    No Known Activations