© 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. 89326
    Prev
    Next
    INDEX
    Explanations

    place and event contexts

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

    Kai’s friend

    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
     τῶν
    0.49
     stunning
    0.49
    いきます
    0.46
    ℍ
    0.46
     የአ
    0.45
     engages
    0.45
     algorithmic
    0.45
     Stunning
    0.45
     Engine
    0.45
     h
    0.44
    POSITIVE LOGITS
     manhã
    0.52
     teníamos
    0.50
     blushed
    0.48
     estaban
    0.48
     tenían
    0.48
     tenía
    0.46
     parecía
    0.45
     hambre
    0.44
     mắn
    0.44
    悻
    0.44
    Activations Density 0.001%

    No Known Activations