© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9710
    Prev
    Next
    INDEX
    Explanations

    evening and night

    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
    ت
    2.45
    t
    2.43
    el
    2.28
    ुन
    2.27
    m
    2.24
    te
    2.20
    ต์
    2.18
    р
    2.08
    ल
    2.04
    тину
    2.00
    POSITIVE LOGITS
    fall
    2.75
    𝐫
    2.71
    gown
    2.53
    theless
    2.45
    𝐡
    2.39
    ்
    2.39
    го
    2.38
    ../../
    2.36
    𝐥
    2.33
    𝐧
    2.33
    Activations Density 0.068%

    No Known Activations