© 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. 4695
    Prev
    Next
    INDEX
    Explanations

    gratitude for

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

    expressing gratitude and intensity

    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
     oppure
    0.40
    fähig
    0.37
    ordu
    0.36
    ος
    0.36
     faintly
    0.36
    ̻
    0.35
     risult
    0.34
     செய்யலாம்
    0.34
     nettement
    0.34
    ferred
    0.34
    POSITIVE LOGITS
     столь
    0.82
     এতো
    0.76
     এত
    0.64
     इतनी
    0.61
    这么
    0.58
     इतने
    0.57
    這麼
    0.57
    这么多
    0.56
     🙏
    0.52
    素晴らしい
    0.52
    Activations Density 0.229%

    No Known Activations