© 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. 34-GEMMASCOPE-RES-131K
    7. 91599
    Prev
    Next
    INDEX
    Explanations

    software rights and conditions

    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
     like
    -1.45
     or
    -1.09
     all
    -1.08
     their
    -1.02
     hjemmeside
    -0.95
    átní
    -0.94
    öße
    -0.94
     negara
    -0.91
    čním
    -0.85
     even
    -0.84
    POSITIVE LOGITS
    がありますが
    1.02
    particularly
    1.01
    Aufbau
    0.99
    Familien
    0.97
    Bewertung
    0.95
     liegenden
    0.94
     insbesondere
    0.92
     colorés
    0.88
     crippled
    0.86
    Vorte
    0.85
    Activations Density 0.004%

    No Known Activations