© 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. 9357
    Prev
    Next
    INDEX
    Explanations

    semicolon after script commands

    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
    त्मक
    1.99
    hearted
    1.85
    Ω
    1.71
    ward
    1.67
     ओर
    1.66
     fact
    1.64
    𝐃
    1.62
    ɴ
    1.61
    eous
    1.58
    ष्‍ट्र
    1.55
    POSITIVE LOGITS
    ل
    2.62
    ли
    2.07
    С
    2.04
    rijven
    2.02
    त
    2.00
     woll
    1.98
    ר
    1.97
    𝘬
    1.96
    kens
    1.91
    रियो
    1.86
    Activations Density 0.001%

    No Known Activations