© 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. 197494
    Prev
    Next
    INDEX
    Explanations

    Filipino prefix 'nak-' / 'mak-'

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

    human wants, constantly processing, melting

    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
    Timing
    0.49
    Tracking
    0.46
    align
    0.43
    蝇
    0.43
    Cycling
    0.42
    思考
    0.41
    Harvest
    0.41
    ajući
    0.40
    जिसे
    0.40
    öst
    0.39
    POSITIVE LOGITS
     LCCN
    0.50
     culprits
    0.45
     即
    0.45
     ơi
    0.44
     ਤੋਂ
    0.43
     site
    0.43
     gt
    0.43
    IMENTS
    0.43
    !;
    0.42
     ประมาณ
    0.42
    Activations Density 0.002%

    No Known Activations