© 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. 173771
    Prev
    Next
    INDEX
    Explanations

    accepting or receiving

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

    receiving or inputting data

    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
    残留
    0.52
    мин
    0.44
    玟
    0.43
     चिंतन
    0.42
    慗
    0.41
    ミン
    0.40
    เศษ
    0.40
     исход
    0.40
     मिन
    0.39
    峎
    0.39
    POSITIVE LOGITS
     receiving
    1.15
     Receiving
    1.09
    接收
    1.09
     recept
    1.05
     recipient
    1.04
     receptive
    1.03
     receptor
    1.02
    receiving
    1.01
     receiver
    0.98
    受け
    0.96
    Activations Density 0.410%

    No Known Activations