© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8795
    Prev
    Next
    INDEX
    Explanations

    negation prefixes and continuations

    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
    𝐬
    2.64
    𝐝
    2.51
    𝐥
    2.49
    𝐫
    2.47
    𝐭
    2.36
    𝐧
    2.35
    oooo
    2.25
    𝐚
    2.23
    ている
    2.18
    oooooooo
    2.17
    POSITIVE LOGITS
    s
    2.67
    т
    2.54
    ת
    2.27
    માં
    2.20
    ের
    2.16
    i
    1.95
    й
    1.95
    ات
    1.91
    te
    1.82
    ի
    1.81
    Activations Density 0.111%

    No Known Activations