© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75697
    Prev
    Next
    INDEX
    Explanations

    past perfect tense

    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
     دید
    0.57
    olds
    0.54
    icklabels
    0.49
    ijk
    0.49
    ,...
    0.45
    umps
    0.43
     들
    0.42
     ذه
    0.41
    ijke
    0.41
    owels
    0.41
    POSITIVE LOGITS
    خدم
    0.44
     nouveau
    0.43
     robotics
    0.43
     Lebens
    0.41
    纓
    0.41
     Zem
    0.40
     major
    0.40
     Syracuse
    0.40
     new
    0.40
     soyez
    0.40
    Activations Density 0.003%

    No Known Activations