© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91367
    Prev
    Next
    INDEX
    Explanations

    reliability or will be lost

    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
    鳳
    -0.81
    ,$
    -0.73
    évé
    -0.73
    ׀
    -0.73
    岭
    -0.69
    Preheat
    -0.69
    eqnarray
    -0.68
    <!--[
    -0.67
    ла
    -0.66
    Font
    -0.66
    POSITIVE LOGITS
     فانت
    0.91
    AGGIO
    0.84
     olması
    0.78
    ctivos
    0.78
     tady
    0.77
    IFER
    0.77
    訃
    0.77
    jauh
    0.76
    ihnachten
    0.75
     tranqu
    0.75
    Activations Density 0.047%

    No Known Activations