© 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. 116304
    Prev
    Next
    INDEX
    Explanations

    question markers and documentation separators

    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
     those
    -1.18
     its
    -1.15
     other
    -1.11
     both
    -1.08
     more
    -1.04
     from
    -1.04
     different
    -1.02
     small
    -0.99
     others
    -0.98
     get
    -0.97
    POSITIVE LOGITS
     также
    1.14
    }/*
    1.00
    expects
    0.99
     inept
    0.97
     גם
    0.96
    .},
    0.95
     أيضًا
    0.92
     også
    0.91
     incapac
    0.91
     conspir
    0.91
    Activations Density 0.000%

    No Known Activations