© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177381
    Prev
    Next
    INDEX
    Explanations

    cement mill

    np_acts-logits-general · gemini-2.5-flash-lite

    singular gender-neutral pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ലഭ്യ
    0.49
     ciência
    0.47
     copos
    0.47
    ווי
    0.46
     गी
    0.46
    Ṕ
    0.46
     ప్రత్య
    0.46
     sedang
    0.46
     ني
    0.45
    ייש
    0.45
    POSITIVE LOGITS
     Criteria
    0.46
    फारिश
    0.46
     Markers
    0.44
     bylaws
    0.42
     ribosomes
    0.41
     anchors
    0.41
     rafts
    0.41
     Sarat
    0.40
    চ্যুত
    0.40
     $<\
    0.40
    Activations Density 0.000%

    No Known Activations