© 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-262K
    7. 9094
    Prev
    Next
    INDEX
    Explanations

    end of question or quote

    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_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
    𝘯
    1.21
     próxim
    1.04
    iary
    1.00
     biogas
    0.98
    ನಿರ್
    0.97
     francis
    0.97
    esorios
    0.96
    ophones
    0.96
     použití
    0.96
     Laravel
    0.95
    POSITIVE LOGITS
    ے
    1.05
     vehemently
    0.93
    ق
    0.92
    în
    0.87
    ren
    0.85
    '.
    0.85
     lamented
    0.84
    ี้
    0.83
    јан
    0.83
    he
    0.82
    Activations Density 1.012%

    No Known Activations