© 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. 10400
    Prev
    Next
    INDEX
    Explanations

    key findings section

    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
     तरह
    2.96
    IDAD
    2.54
     Damn
    2.50
    ডো
    2.34
    𝑒
    2.24
    ia
    2.20
    RCT
    2.17
    पृथ
    2.16
     дру
    2.16
    繹
    2.15
    POSITIVE LOGITS
    _{
    3.01
    তিত
    2.83
    britannien
    2.65
    <unused2222>
    2.59
    aulay
    2.56
    ৪
    2.55
    ter
    2.55
    رات
    2.54
    تع
    2.54
    การ
    2.52
    Activations Density 0.015%

    No Known Activations