© 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. 49784
    Prev
    Next
    INDEX
    Explanations

    unique character and charm

    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
    similar
    -0.91
     semblable
    -0.88
     sellado
    -0.87
     sumptuous
    -0.87
    lieving
    -0.86
     deberes
    -0.84
    ocrats
    -0.84
    mler
    -0.83
     flashy
    -0.83
    ridis
    -0.82
    POSITIVE LOGITS
     charm
    3.44
    charm
    2.52
     character
    2.47
     Charm
    2.25
    Charm
    2.16
     charms
    2.09
     charming
    2.06
     endearing
    1.98
     charme
    1.90
     charmed
    1.81
    Activations Density 0.032%

    No Known Activations