© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6996
    Prev
    Next
    INDEX
    Explanations

    cats marking territorial scents

    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
    firestore
    1.18
    
    1.17
    nashville
    1.13
    来店
    1.08
    lc
    1.06
     एनसी
    1.04
    pecia
    1.03
    ᱚ
    1.03
    indian
    1.03
    ecc
    1.02
    POSITIVE LOGITS
     parrot
    0.98
     should
    0.94
     bill
    0.93
     elif
    0.88
    riad
    0.86
     float
    0.85
     aside
    0.84
    мули
    0.84
     shouldn
    0.83
     unaltered
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.