© 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. 21914
    Prev
    Next
    INDEX
    Explanations

    emotional response to illness or diagnosis

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

    emotional reactions, grief, or surprise

    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
     χρησιμοποι
    0.49
     Computing
    0.46
     ưa
    0.42
    Computing
    0.42
     USING
    0.41
     використання
    0.41
    槓
    0.41
    ベン
    0.39
     Drop
    0.39
    使用
    0.38
    POSITIVE LOGITS
     emotional
    0.69
     shocked
    0.68
     emocional
    0.67
     stigmat
    0.66
     emotionally
    0.66
    emotional
    0.65
     psychosocial
    0.64
     shock
    0.64
     frighten
    0.64
     anxieties
    0.63
    Activations Density 0.110%

    No Known Activations