© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1406
    Prev
    Next
    INDEX
    Explanations

    suggesting alternative actions or topics

    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_13_width_65k_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
     листь
    1.11
    <0x0C>
    1.09
    achtree
    1.05
    รถ
    1.04
    và
    1.03
    ĸ
    1.02
     бюджета
    1.02
    ỷ
    1.01
     จาก
    1.00
    </td>
    0.99
    POSITIVE LOGITS
     essentially
    1.44
     conceivably
    1.37
     greatly
    1.33
     theoretically
    1.30
     easily
    1.27
     ordinarily
    1.26
     effectively
    1.25
     be
    1.25
     realistically
    1.24
     significantly
    1.14
    Activations Density 1.257%

    No Known Activations