© 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. 22677
    Prev
    Next
    INDEX
    Explanations

    launching programs and initiatives

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

    quoted titles and specific concepts

    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
    該当
    0.47
     lunghezza
    0.47
     DESCRIPTION
    0.45
    ！！！！
    0.44
     একদিকে
    0.44
     २
    0.44
    早く
    0.44
    死去
    0.44
     ।”
    0.43
     från
    0.43
    POSITIVE LOGITS
     Program
    0.71
     Initiative
    0.70
     Diploma
    0.64
     Scholarship
    0.64
     برنامج
    0.64
     initiative
    0.63
     Awards
    0.62
     Passport
    0.59
     Invitational
    0.59
     Programa
    0.59
    Activations Density 0.228%

    No Known Activations