© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9835
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing 'in', 'ine', 'ina'

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

    words ending with in

    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_40_width_16k_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
    یه
    0.42
    িব
    0.41
    inplace
    0.41
    ी
    0.41
    之后的
    0.40
    即使
    0.40
    ிருப்ப
    0.40
     deleniti
    0.40
    .??.??"]
    0.40
    迩
    0.39
    POSITIVE LOGITS
    ny
    0.71
    ners
    0.68
    nesota
    0.64
    ning
    0.63
    novation
    0.60
    shaw
    0.57
    ctor
    0.56
    ette
    0.55
    obu
    0.55
    stitute
    0.55
    Activations Density 1.099%

    No Known Activations