© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    thought patterns

    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
    o
    2.81
    ம்
    2.67
    oooo
    2.54
    Между
    2.52
    ている
    2.41
    ről
    2.39
    ooo
    2.36
    ev
    2.35
    ców
    2.32
    у
    2.27
    POSITIVE LOGITS
    astly
    2.63
     viewModel
    2.50
    💭
    2.49
    ส์
    2.49
    andfeel
    2.48
    $('#
    2.40
    provoking
    2.37
     zeroth
    2.35
     rename
    2.34
     handheld
    2.29
    Activations Density 0.251%

    No Known Activations