© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7113
    Prev
    Next
    INDEX
    Explanations

    printing output in scripts

    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_22_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
    MLE
    0.78
    衙
    0.75
    ществ
    0.75
    Although
    0.70
    薷
    0.69
     дре
    0.69
    Aunque
    0.68
    allows
    0.67
     એવી
    0.67
     geographical
    0.67
    POSITIVE LOGITS
     cilind
    0.76
     Nested
    0.74
    abend
    0.73
     Schulen
    0.70
     $<
    0.69
     dollari
    0.68
    Billing
    0.67
    nested
    0.67
     stood
    0.66
     inline
    0.65
    Activations Density 0.008%

    No Known Activations