© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9929
    Prev
    Next
    INDEX
    Explanations

    locations tucked away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     underpinning
    1.01
     reaching
    0.88
     manne
    0.88
    zes
    0.82
     चलाया
    0.82
     বিস্ত
    0.82
     жү
    0.82
    圭
    0.82
    ⅛
    0.81
    சம்
    0.80
    POSITIVE LOGITS
     date
    1.37
     anniversary
    1.33
     Ceremon
    1.31
     ceremony
    1.30
    date
    1.30
     Celebration
    1.24
     Ceremony
    1.24
     celebration
    1.20
     celebrations
    1.20
    日期
    1.15
    Activations Density 0.165%

    No Known Activations