© 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. 98268
    Prev
    Next
    INDEX
    Explanations

    agenda and related

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

    swallowed whole

    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
    伍章
    0.49
     Deutsches
    0.48
     अणुओं
    0.48
     उपयुक्त
    0.48
    DAAR
    0.47
     नागरिक
    0.46
     ૩
    0.46
     जल
    0.46
     பறி
    0.46
     दस
    0.46
    POSITIVE LOGITS
     agenda
    0.53
     agendas
    0.50
    Agenda
    0.46
    rotz
    0.46
    set
    0.45
    첼
    0.45
     Agenda
    0.44
    ref
    0.44
    ropath
    0.43
     conversa
    0.42
    Activations Density 0.000%

    No Known Activations