© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 4017
    Prev
    Next
    INDEX
    Explanations

    determiners, auxiliaries, interrogatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    !),
    0.42
    ・
    0.40
     though
    0.37
     వాటి
    0.37
    ・・・
    0.37
    awat
    0.37
    !).
    0.36
    /
    0.36
     pues
    0.36
     \(
    0.36
    POSITIVE LOGITS
    exactly
    0.52
    really
    0.52
    thirty
    0.48
    first
    0.45
    two
    0.44
    before
    0.44
    last
    0.43
    only
    0.43
    already
    0.43
    “…
    0.43
    Activations Density 0.706%

    No Known Activations