© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8585
    Prev
    Next
    INDEX
    Explanations

    inflation above target

    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
     "
    1.03
     feet
    0.98
     '
    0.97
     mask
    0.93
     link
    0.90
     march
    0.90
     start
    0.90
     venture
    0.89
     parallels
    0.88
     miles
    0.88
    POSITIVE LOGITS
    <unused1353>
    1.64
    <unused1477>
    1.62
    <unused1339>
    1.57
     ويك
    1.54
     يك
    1.53
    ርድ
    1.53
    高考
    1.52
    <unused1472>
    1.52
    <unused1394>
    1.52
    <unused1429>
    1.51
    Activations Density 0.000%

    No Known Activations