© 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. 11614
    Prev
    Next
    INDEX
    Explanations

    presence for a purpose

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

    here to assist

    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_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
    进来
    0.45
     लगे
    0.43
     عالم
    0.43
     saída
    0.42
     알파
    0.40
     상태
    0.40
     обратно
    0.39
    爨
    0.39
     фон
    0.39
    ティー
    0.39
    POSITIVE LOGITS
     forefront
    0.48
    gerald
    0.45
    stays
    0.43
     promoting
    0.43
    picks
    0.43
    moral
    0.42
    elio
    0.41
    promoting
    0.41
    ispielsweise
    0.40
     moral
    0.40
    Activations Density 0.110%

    No Known Activations