© 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. 18366
    Prev
    Next
    INDEX
    Explanations

    reserve or reserved rights

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

    reserves the right

    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
    在
    0.60
     endeavors
    0.54
     in
    0.54
     valida
    0.52
     obten
    0.50
     vær
    0.50
    在前
    0.50
     (_,
    0.50
     Tree
    0.49
     quies
    0.49
    POSITIVE LOGITS
    reserved
    1.20
     reserved
    1.05
    Reserved
    1.02
     Reserved
    1.02
    reserve
    1.01
     reserve
    0.91
     Reserv
    0.89
     reserva
    0.88
     riserv
    0.86
     rezerv
    0.85
    Activations Density 0.026%

    No Known Activations