Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8575
    Prev
    Next
    INDEX
    Explanations

    people's 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_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
    right
    -0.92
    時間を
    -0.91
    だったが
    -0.89
     is
    -0.88
    を見つけ
    -0.88
     didn
    -0.85
     could
    -0.85
    App
    -0.85
     خمس
    -0.84
     «
    -0.84
    POSITIVE LOGITS
    érant
    1.28
     estadísticas
    1.23
    ्ञ
    1.19
    verzeichnis
    1.16
    catori
    1.13
    liferation
    1.13
     appré
    1.12
    ofern
    1.12
    ffeine
    1.12
    sste
    1.11
    Activations Density 0.085%

    No Known Activations