© 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. 186025
    Prev
    Next
    INDEX
    Explanations

    lifelong resident

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

    elevate above

    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
    门
    0.45
    Las
    0.44
    SAF
    0.43
     confirma
    0.43
     Eul
    0.43
    IDS
    0.42
     Gateway
    0.42
    мести
    0.42
    URA
    0.41
    Gateway
    0.41
    POSITIVE LOGITS
     رکھیں
    0.49
    笑
    0.45
    音樂
    0.45
     radionuclide
    0.44
     یوں
    0.42
    早い
    0.42
     music
    0.42
     음악
    0.42
    美味しい
    0.42
    レント
    0.42
    Activations Density 0.000%

    No Known Activations