© 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. 9582
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

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

    personal life events and situations

    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
     దాని
    0.42
    ünft
    0.41
    我們
    0.40
    スク
    0.39
     तसेच
    0.38
     清
    0.37
    他們
    0.37
    តិ
    0.37
    eden
    0.37
    acterial
    0.37
    POSITIVE LOGITS
     flirt
    0.47
     yaşad
    0.47
     menikah
    0.46
     Guggenheim
    0.46
     winnings
    0.46
     controvers
    0.45
     famously
    0.45
     married
    0.44
     Yale
    0.44
     romant
    0.44
    Activations Density 0.039%

    No Known Activations