© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48466
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     what
    -1.01
     should
    -0.98
     those
    -0.95
     forty
    -0.94
     by
    -0.94
     considère
    -0.93
     fifty
    -0.93
     hundreds
    -0.92
    東南
    -0.91
    utilité
    -0.90
    POSITIVE LOGITS
     två
    1.12
    UNITIES
    0.99
     flera
    0.99
     människor
    0.96
    ξεις
    0.94
     Indic
    0.92
    зм
    0.90
    Ί
    0.90
    bilidade
    0.90
     incluindo
    0.90
    Activations Density 0.018%

    No Known Activations