© 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-262K
    7. 13582
    Prev
    Next
    INDEX
    Explanations

    summarizing introduction

    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_262k_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
     очередной
    0.86
    *.
    0.86
    ®.
    0.84
     Another
    0.84
    ");</
    0.80
    Another
    0.80
    攵
    0.78
    ().
    0.78
    ™.
    0.76
    .",
    0.75
    POSITIVE LOGITS
     essentially
    1.43
     basically
    1.41
     also
    1.39
     גם
    1.36
     myös
    1.35
     juga
    1.28
     inoltre
    1.26
     همچنین
    1.25
     cũng
    1.25
     также
    1.25
    Activations Density 0.293%

    No Known Activations