© 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. 5711
    Prev
    Next
    INDEX
    Explanations

    outcome and result descriptions

    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
    льною
    1.48
     সম্পাদকীয়
    1.40
    concepts
    1.38
    deficient
    1.37
    locations
    1.37
    <unused2034>
    1.36
    <unused501>
    1.36
    only
    1.36
    STRA
    1.35
    <unused1829>
    1.35
    POSITIVE LOGITS
    пад
    0.95
     brim
    0.88
     or
    0.88
     brit
    0.88
    ↵↵
    0.86
     ah
    0.85
     spark
    0.84
     kry
    0.84
     yen
    0.83
     bet
    0.82
    Activations Density 0.197%

    No Known Activations