© 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. 182122
    Prev
    Next
    INDEX
    Explanations

    prospective parents

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

    while introducing a contrast or qualification

    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
    Callbacks
    0.49
    тів
    0.47
    쵸
    0.47
    Encryption
    0.45
    各種
    0.43
    Revolution
    0.43
    各种
    0.42
    ײ
    0.42
    Motor
    0.41
    ոտ
    0.41
    POSITIVE LOGITS
     kulit
    0.55
    அது
    0.52
     desped
    0.49
     conservar
    0.49
     teng
    0.49
     chamado
    0.48
     கூறிய
    0.48
     disimpan
    0.47
     acara
    0.47
    ষ
    0.46
    Activations Density 0.001%

    No Known Activations