© 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. 62388
    Prev
    Next
    INDEX
    Explanations

    to call / to receive

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

    explaining the 'why'

    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
    গুল
    0.43
    owią
    0.40
     hiển
    0.40
    硖
    0.39
    显示
    0.38
    자기
    0.38
     $.
    0.38
    documents
    0.37
    ප
    0.37
    ównie
    0.37
    POSITIVE LOGITS
     PFAS
    0.52
     DeFi
    0.51
     anthe
    0.49
     मानसिकता
    0.49
     pozitiv
    0.48
     outspoken
    0.48
     advocating
    0.48
     peningkatan
    0.47
     resistance
    0.47
     agonist
    0.47
    Activations Density 0.000%

    No Known Activations