© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8372
    Prev
    Next
    INDEX
    Explanations

    learns patterns and trends

    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
    <b>
    1.30
    </i>
    1.10
    </td>
    1.09
    kommen
    1.05
    árt
    1.03
    </th>
    0.92
    arnos
    0.91
    \")
    0.90
    del
    0.89
    avec
    0.88
    POSITIVE LOGITS
     同时
    1.44
     也
    1.41
     READ
    1.39
     irony
    1.38
     因此
    1.36
     VIEW
    1.34
    <em>
    1.33
     notion
    1.31
     令
    1.29
     resultant
    1.28
    Activations Density 0.000%

    No Known Activations