© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38176
    Prev
    Next
    INDEX
    Explanations

    Sax fanfiction

    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
     esimerkiksi
    -0.79
    đu
    -0.75
     hers
    -0.74
     protections
    -0.71
     skai
    -0.70
    🦳
    -0.70
    Etern
    -0.70
    diente
    -0.69
     Wydawnictwo
    -0.69
     mails
    -0.68
    POSITIVE LOGITS
    jacking
    0.82
     chiama
    0.78
     continú
    0.75
     Sax
    0.75
     início
    0.74
     colesterol
    0.74
     charakterysty
    0.74
    淘宝
    0.73
    Sax
    0.72
     fanfiction
    0.72
    Activations Density 0.004%

    No Known Activations