© 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. 122547
    Prev
    Next
    INDEX
    Explanations

    signs and billboards

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

    signs and signage

    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
     injecting
    0.48
     performed
    0.45
     सेमेस्टर
    0.44
    屜
    0.44
     notebook
    0.42
     injected
    0.41
     Surface
    0.41
     packed
    0.40
     Fakt
    0.40
     encrypt
    0.39
    POSITIVE LOGITS
     roadside
    0.89
     billboards
    0.79
    看板
    0.79
     billboard
    0.71
    掲
    0.66
     signage
    0.65
    Billboard
    0.63
    banners
    0.63
     banners
    0.63
     Posters
    0.60
    Activations Density 0.113%

    No Known Activations