© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11845
    Prev
    Next
    INDEX
    Explanations

    halloween and autumn events

    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
    t
    2.90
    저
    2.87
    ed
    2.74
    ि
    2.42
    kommen
    2.39
    𝚃
    2.39
    istence
    2.36
    𝚍
    2.36
    re
    2.35
    ვ
    2.33
    POSITIVE LOGITS
    eine
    2.65
    ного
    2.62
     sputter
    2.55
    ی
    2.46
    ,\,
    2.43
    ට
    2.43
    ्हे
    2.40
    ে
    2.39
    чески
    2.38
    ular
    2.35
    Activations Density 0.022%

    No Known Activations