© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5416
    Prev
    Next
    INDEX
    Explanations

    mathematical notation variable prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ૪
    0.95
     $+$
    0.88
    }=-
    0.85
     $+
    0.84
    imt
    0.82
    či
    0.82
     $|\
    0.81
    proud
    0.81
     $+\
    0.81
     $:=$
    0.80
    POSITIVE LOGITS
     hiring
    0.85
     Salut
    0.84
     defying
    0.82
     Bathroom
    0.81
     Welch
    0.80
     microphone
    0.78
     perennial
    0.77
     rock
    0.76
     AppDelegate
    0.76
    SAFETY
    0.76
    Activations Density 0.138%

    No Known Activations