© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    United States / occurs depends / Fully correct

    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_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
     pobl
    0.97
    amsa
    0.96
    .\
    0.94
     ওভার
    0.93
     ওয়
    0.90
    र
    0.89
    wares
    0.89
     पाण्डेय
    0.89
    asa
    0.89
    kar
    0.87
    POSITIVE LOGITS
     unequivocal
    1.50
     unambiguous
    1.34
     hemicontinuous
    1.31
    ष्टमी
    1.28
     Alban
    1.27
    <unused2140>
    1.27
     repatri
    1.25
     interleaved
    1.24
     sostanz
    1.23
     contemporaneous
    1.21
    Activations Density 0.000%

    No Known Activations