© 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. 31319
    Prev
    Next
    INDEX
    Explanations

    describing characters' feelings and traits

    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
    atious
    -0.92
    égias
    -0.86
    uel
    -0.80
    igan
    -0.79
    onomies
    -0.79
    frames
    -0.77
    戊
    -0.75
    item
    -0.74
    eses
    -0.74
    담
    -0.73
    POSITIVE LOGITS
     fles
    1.70
     believable
    1.63
     developed
    1.62
     flawed
    1.53
     lik
    1.52
     memorable
    1.45
     characters
    1.44
     dimensional
    1.41
     complex
    1.34
     character
    1.32
    Activations Density 0.027%

    No Known Activations