© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6807
    Prev
    Next
    INDEX
    Explanations

    Dragon Fruit, Monkey Island, fish, triangle area

    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
    ו
    1.96
    $/../../
    1.84
    amente
    1.83
    s
    1.82
    ümü
    1.76
    ל
    1.69
    ш
    1.63
    いる
    1.61
     médico
    1.61
    뷔
    1.61
    POSITIVE LOGITS
    shaped
    2.18
    flies
    1.97
    fasta
    1.96
    fish
    1.93
     nurture
    1.93
     lemma
    1.92
    docx
    1.92
    로
    1.90
    од
    1.89
     symbolize
    1.87
    Activations Density 0.610%

    No Known Activations