© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3932
    Prev
    Next
    INDEX
    Explanations

    Error Handling

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵↵↵↵↵↵↵
    1.50
     Abgerufen
    1.49
    ↵↵↵↵↵
    1.43
    सूची
    1.37
     przechowy
    1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.34
    Keys
    1.33
     teşekkür
    1.32
     jaką
    1.32
    الس
    1.31
    POSITIVE LOGITS
    sized
    1.43
     seemingly
    1.39
    ­
    1.35
    borders
    1.35
    roof
    1.33
     introductory
    1.30
     lucrative
    1.30
    hov
    1.30
     homogenous
    1.29
    layered
    1.28
    Activations Density 0.002%

    No Known Activations