© 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. 9436
    Prev
    Next
    INDEX
    Explanations

    efficient operation or processing

    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
     appBar
    3.07
    ৯
    2.86
     termine
    2.84
    னர்
    2.72
    ipitation
    2.69
     etiam
    2.65
    कर
    2.60
    ίες
    2.57
    ̳
    2.55
    ভূতি
    2.55
    POSITIVE LOGITS
    u
    4.13
    i
    3.50
    ش
    3.45
    ം
    3.37
    d
    3.36
    o
    3.29
    t
    3.17
    ल
    3.08
    e
    3.05
    יות
    2.89
    Activations Density 0.122%

    No Known Activations