© 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. 61640
    Prev
    Next
    INDEX
    Explanations

    specific phrases and titles

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

    case-by-case; liquid; shame; achieving

    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
     נישט
    0.53
    唃
    0.48
    פים
    0.47
    کنش
    0.46
    噙
    0.46
    垕
    0.45
    衝撃
    0.45
     полного
    0.44
    скага
    0.44
    鑰
    0.44
    POSITIVE LOGITS
    occur
    0.50
     contends
    0.50
     etiquetas
    0.50
    lcc
    0.50
     occur
    0.48
     invariably
    0.48
     coexist
    0.48
    itesi
    0.48
     weaves
    0.48
    chés
    0.47
    Activations Density 0.001%

    No Known Activations