© 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. 9366
    Prev
    Next
    INDEX
    Explanations

    very much

    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
    ب
    3.63
    𝒈
    3.00
    𝘷
    2.96
    kannya
    2.95
    𝘫
    2.94
    𝒗
    2.93
    𝘨
    2.75
    𝒔
    2.73
    𝒋
    2.70
    𝒓
    2.66
    POSITIVE LOGITS
    daki
    2.62
     الحياة
    2.61
     aware
    2.60
    rooted
    2.51
    alive
    2.46
    ης
    2.43
     ERK
    2.39
    다
    2.39
     situés
    2.37
     العزيز
    2.35
    Activations Density 0.014%

    No Known Activations