© 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. 24042
    Prev
    Next
    INDEX
    Explanations

    introduces something

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

    articles like 'a' and 'an'

    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
    able
    0.65
    ers
    0.61
    0
    0.59
    2
    0.59
    ly
    0.57
    ures
    0.57
    uring
    0.56
    as
    0.56
    }-\
    0.55
    which
    0.54
    POSITIVE LOGITS
     një
    0.91
     એક
    0.89
     một
    0.85
     μια
    0.85
     ایک
    0.84
     ένα
    0.79
     a
    0.79
     একটি
    0.75
     sebuah
    0.75
     ஓர்
    0.75
    Activations Density 0.079%

    No Known Activations