© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155842
    Prev
    Next
    INDEX
    Explanations

    shyness and awkwardness

    np_acts-logits-general · gemini-2.5-flash-lite

    nervousness and awkwardness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𓂀
    0.47
     TRUST
    0.43
    嘲
    0.43
    Mono
    0.42
    Joke
    0.42
    啁
    0.41
     provocar
    0.41
    Noun
    0.41
    悠
    0.40
    鼓勵
    0.39
    POSITIVE LOGITS
     nervously
    1.20
     nervousness
    1.05
     nervous
    1.02
     afraid
    0.98
     panicked
    0.98
     panic
    0.98
     awkward
    0.97
     awkwardly
    0.95
    害怕
    0.94
    慌
    0.91
    Activations Density 0.150%

    No Known Activations