© 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. 55822
    Prev
    Next
    INDEX
    Explanations

    Real-Time Text Technology

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

    explaining cloud platforms

    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
    EDB
    0.52
    ILA
    0.46
    වේ
    0.43
    Boy
    0.42
    TECH
    0.41
    EK
    0.41
    Powell
    0.41
    팜
    0.40
    ون
    0.40
    EEK
    0.40
    POSITIVE LOGITS
     orthogonality
    0.50
    ন
    0.46
     MMS
    0.45
     Nautilus
    0.45
     Vf
    0.45
     രാഷ്ട്രീയ
    0.45
     bellows
    0.45
     eau
    0.44
     طبیعت
    0.44
     GLS
    0.44
    Activations Density 0.000%

    No Known Activations