© 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. 41277
    Prev
    Next
    INDEX
    Explanations

    How you feel

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

    Are you asking about current state

    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
     bevest
    0.43
     kết
    0.41
     波
    0.40
     আমাদের
    0.39
     nantinya
    0.39
    氇
    0.39
     Cái
    0.38
    曉
    0.38
     સમગ્ર
    0.38
     chúng
    0.37
    POSITIVE LOGITS
    目前的
    0.47
     currentValue
    0.46
     комфор
    0.45
    目前
    0.45
     comfortable
    0.44
     atualmente
    0.43
    currentItem
    0.43
     کررہ
    0.42
     Comfortable
    0.42
     complacent
    0.42
    Activations Density 0.104%

    No Known Activations