© 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. 31-GEMMASCOPE-2-RES-262K
    7. 7128
    Prev
    Next
    INDEX
    Explanations

    past tense constructions

    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_31_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
    Recently
    0.28
     recientemente
    0.28
     最近
    0.27
    Aquí
    0.27
    最近
    0.27
     Recently
    0.26
    <0x80>
    0.26
    есть
    0.26
    스
    0.25
     escuchado
    0.25
    POSITIVE LOGITS
     a
    0.26
    z
    0.24
     has
    0.24
     on
    0.23
     resemble
    0.23
    ha
    0.23
    akat
    0.23
    k
    0.23
     by
    0.22
    holds
    0.22
    Activations Density 0.054%

    No Known Activations