© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11868
    Prev
    Next
    INDEX
    Explanations

    as long as

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

    as long as

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

    provided

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
    😞
    0.41
     hapless
    0.41
     niest
    0.40
     :/
    0.39
    Unable
    0.39
     :(
    0.39
    észet
    0.39
     compounding
    0.38
     üzere
    0.38
    😖
    0.38
    POSITIVE LOGITS
    只要
    2.28
     Provided
    1.65
     provided
    1.61
    Provided
    1.54
    provided
    1.51
     PROVIDED
    1.37
     যতক্ষণ
    1.29
    PROVIDED
    1.19
     условии
    1.06
    前提
    1.03
    Activations Density 0.485%

    No Known Activations