© 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. 942
    Prev
    Next
    INDEX
    Explanations

    free followed by nouns

    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
    dı
    0.82
    শ
    0.81
     facet
    0.80
    Recogn
    0.80
     UTC
    0.80
    Yb
    0.79
    Ы
    0.79
    ﺎ
    0.78
    mér
    0.77
    ன்
    0.76
    POSITIVE LOGITS
    bies
    2.08
    bie
    1.91
    zing
    1.55
    zers
    1.49
    🆓
    1.36
    롭게
    1.18
    zer
    1.14
     reign
    1.09
    zes
    1.09
    keh
    1.08
    Activations Density 0.169%

    No Known Activations