© 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. 54079
    Prev
    Next
    INDEX
    Explanations

    github urls

    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
    ebly
    -0.95
    などなど
    -0.90
    的问
    -0.89
    tis
    -0.88
     alcune
    -0.86
     I
    -0.85
    が多く
    -0.83
     |]
    -0.82
    atouille
    -0.82
    と思っていた
    -0.81
    POSITIVE LOGITS
    Nachteile
    1.20
    Sprache
    1.15
    Einfach
    1.13
    Leistungs
    1.12
    آموزش
    1.12
    Maße
    1.09
    Lieferumfang
    1.09
     saca
    1.05
    معرفی
    1.02
    Mitte
    1.02
    Activations Density 0.087%

    No Known Activations