© 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. 49365
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings with hyphens

    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
     but
    -1.11
    recent
    -0.98
     pere
    -0.97
    hibitor
    -0.94
    aconda
    -0.92
    though
    -0.90
    Unable
    -0.90
    erobic
    -0.90
    iline
    -0.89
     getResources
    -0.88
    POSITIVE LOGITS
     ИЗ
    0.88
     jeste
    0.87
    ihnach
    0.87
    drip
    0.86
     duomen
    0.83
    Rinse
    0.82
     concom
    0.82
     felicidad
    0.82
    łoży
    0.82
     powi
    0.81
    Activations Density 0.012%

    No Known Activations