© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3250
    Prev
    Next
    INDEX
    Explanations

    words followed by off

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

    ending or negative states with 'off'

    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_53_width_65k_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
    ினர்
    0.35
    igens
    0.35
    ັບ
    0.33
    <!---
    0.33
    懷
    0.33
    കു
    0.32
    של
    0.32
     dalamnya
    0.32
    㗽
    0.32
    дян
    0.31
    POSITIVE LOGITS
     off
    5.31
    off
    4.41
     Off
    4.28
    Off
    4.25
     OFF
    4.09
    オフ
    3.64
     offs
    3.45
    OFF
    3.44
    offs
    3.28
     অফ
    2.94
    Activations Density 0.568%

    No Known Activations