© 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. 98314
    Prev
    Next
    INDEX
    Explanations

    connecting mobile, RS, POP

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

    how to try

    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
     Mandalorian
    0.47
    만큼
    0.47
    ALTERNATIVNAMEN
    0.47
    輋
    0.46
    嫂
    0.46
     만큼
    0.46
     propagand
    0.46
    上帝
    0.45
     Redeemer
    0.45
    사랑
    0.44
    POSITIVE LOGITS
     pairs
    0.50
     connectivity
    0.49
     facilitates
    0.47
     rows
    0.47
     appended
    0.47
     acoustics
    0.47
     х
    0.47
     gateways
    0.47
     clips
    0.46
     electrodes
    0.46
    Activations Density 0.002%

    No Known Activations