© 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. 104475
    Prev
    Next
    INDEX
    Explanations

    rating, versions, I, notified, everything, truly

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

    Variational Autoencoder

    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
     dola
    0.54
     reçu
    0.50
     altri
    0.48
     sofern
    0.48
    RECEIVED
    0.47
     anderer
    0.47
     crece
    0.46
    <0xAC>
    0.46
     dólares
    0.46
     reç
    0.46
    POSITIVE LOGITS
    па
    0.46
    hed
    0.44
    럽
    0.44
    பா
    0.44
    ینا
    0.43
     פאר
    0.43
     시절
    0.43
     奥
    0.43
    >")
    0.42
    iggle
    0.42
    Activations Density 0.000%

    No Known Activations