© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1841
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a word

    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_9_width_16k_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
    ка
    1.49
    이
    1.49
    uff
    1.48
    e
    1.37
    a
    1.35
     brighten
    1.29
    ер
    1.27
    تام
    1.26
    鈽
    1.25
    𝑒
    1.25
    POSITIVE LOGITS
     pihaknya
    1.71
    ंग्रेस
    1.57
    このような
    1.52
     Examinations
    1.43
     Messieurs
    1.41
     Inspectors
    1.40
    Insufficient
    1.40
    äden
    1.39
    soever
    1.37
    ierungen
    1.37
    Activations Density 0.484%

    No Known Activations