© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6844
    Prev
    Next
    INDEX
    Explanations

    talking to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    дени
    1.44
    ﻈ
    1.39
    觉得自己
    1.34
     in
    1.34
    กรณ์
    1.32
    อยู่ใน
    1.32
    ėd
    1.29
    ﺡ
    1.27
     invál
    1.27
    ﺓ
    1.26
    POSITIVE LOGITS
    Vx
    1.99
    Camera
    1.90
    polar
    1.82
    QR
    1.82
    URL
    1.79
    Pix
    1.77
    ADS
    1.76
     url
    1.72
    bore
    1.70
    Message
    1.70
    Activations Density 0.010%

    No Known Activations