© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10058
    Prev
    Next
    INDEX
    Explanations

    filling bracketed text

    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
    عبة
    0.89
    کیل
    0.86
     Komb
    0.84
     konfigur
    0.82
     Decimal
    0.77
     festgelegt
    0.77
    臃
    0.77
     인
    0.76
     kombin
    0.76
     optimised
    0.76
    POSITIVE LOGITS
     mentorship
    1.10
     mentoring
    1.05
     mentors
    1.05
     remarks
    1.05
    strokes
    1.00
    né
    1.00
    placeholder
    0.99
     parlare
    0.99
     applause
    0.99
     mentor
    0.98
    Activations Density 0.050%

    No Known Activations