© 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. 200380
    Prev
    Next
    INDEX
    Explanations

    social dimensions, Spanish Revival, tracking practices, custom made

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

    distance, permitting, amazed, copying, speaking, Amazon, Ataxia, exploiting

    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
    رب
    0.52
    раи
    0.49
     Posteriormente
    0.47
    ед
    0.47
     масла
    0.46
    зой
    0.46
    ियर्स
    0.46
    咟
    0.46
    აზე
    0.46
    ﱢ
    0.46
    POSITIVE LOGITS
    esthetic
    0.49
     เนี่ย
    0.48
    weza
    0.46
    Do
    0.45
    doch
    0.44
     संयोग
    0.44
     concurrence
    0.44
     agility
    0.44
    tedy
    0.44
    dent
    0.43
    Activations Density 0.000%

    No Known Activations