© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 584
    Prev
    Next
    INDEX
    Explanations

    reporting speech or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shout
    1.07
    ্পনিক
    1.03
    o
    1.02
    er
    1.02
    ity
    1.01
     embrace
    0.97
    ص
    0.96
    ri
    0.96
    பு
    0.95
     encompassed
    0.94
    POSITIVE LOGITS
     bahwa
    1.52
     Alguns
    1.37
     bellezza
    1.35
     bilangan
    1.34
     Também
    1.34
    tahun
    1.33
    這是
    1.31
     moteurs
    1.27
     cidades
    1.26
    Het
    1.25
    Activations Density 0.121%

    No Known Activations