© 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. 90167
    Prev
    Next
    INDEX
    Explanations

    action, progress, and goals

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

    policy and procedure outlines

    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
    வனுக்கு
    0.44
    BODY
    0.44
     innumerable
    0.44
    Science
    0.44
    Hara
    0.41
     COLOR
    0.41
    
    0.40
    直至
    0.40
     мировой
    0.39
    τί
    0.38
    POSITIVE LOGITS
    ⁤
    0.66
    ⁢
    0.53
    🥲
    0.53
    openai
    0.51
     openai
    0.51
     tiktok
    0.51
    🫶
    0.51
     ২০২৩
    0.50
     Ancak
    0.48
    🥹
    0.47
    Activations Density 0.082%

    No Known Activations