© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 15557
    Prev
    Next
    INDEX
    Explanations

    had been or had + past participle

    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_16_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
    on
    1.47
     you
    1.15
    انی
    1.10
    ای
    1.09
    ین
    1.03
    and
    0.99
    ہ
    0.98
    ación
    0.98
    на
    0.95
    ะ
    0.95
    POSITIVE LOGITS
     in
    1.55
    ي
    1.55
    to
    1.48
    с
    1.27
    的三
    1.27
    在
    1.23
    的老
    1.20
    n
    1.20
    ;
    1.19
    ని
    1.13
    Activations Density 0.032%

    No Known Activations