© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3613
    Prev
    Next
    INDEX
    Explanations

    reproducible results and environments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝙀
    1.61
    𝙉
    1.60
    ចែក
    1.59
    𝙎
    1.58
     समाज
    1.58
    AddModel
    1.56
    ਾਨ
    1.56
    我国
    1.56
    ራስ
    1.54
    𝙢
    1.54
    POSITIVE LOGITS
    ),
    1.79
    ).
    1.75
    .
    1.58
    ,
    1.56
    )
    1.44
     is
    1.43
     says
    1.40
     provides
    1.37
     has
    1.32
     heeft
    1.31
    Activations Density 0.278%

    No Known Activations