© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 15292
    Prev
    Next
    INDEX
    Explanations

    item, Provider, therapy, motion, want

    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_17_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
    ędzy
    1.20
    ুপ
    0.96
    ̰
    0.95
     linseed
    0.94
    वीन
    0.92
     반복
    0.92
     bumpy
    0.90
    блица
    0.90
    éna
    0.89
    বৃত্তি
    0.89
    POSITIVE LOGITS
    ']
    1.06
    '],
    1.01
    '].
    0.95
    ',
    0.93
    at
    0.88
    ?',
    0.86
    ']}
    0.85
     pula
    0.84
    of
    0.83
    '.$
    0.83
    Activations Density 0.120%

    No Known Activations