© 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. 143759
    Prev
    Next
    INDEX
    Explanations

    greeting + occasion

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

    happy greetings and phrases

    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
    K
    0.68
    ক
    0.67
    ف
    0.66
    क
    0.65
    F
    0.61
    𝗚
    0.61
    𝗬
    0.60
    R
    0.59
    Fue
    0.58
    গত
    0.58
    POSITIVE LOGITS
     happy
    0.86
     Happy
    0.82
     feliz
    0.76
     HAPPY
    0.74
     mutlu
    0.71
     felices
    0.66
    happy
    0.66
     bahagia
    0.63
     happier
    0.61
    HAPPY
    0.59
    Activations Density 0.079%

    No Known Activations