© 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. 178827
    Prev
    Next
    INDEX
    Explanations

    NHS patients, sunny weather, archaic "thee"

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

    spot common errors

    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
    s
    0.58
    is
    0.53
    Keys
    0.52
    keys
    0.50
    Ana
    0.49
    Records
    0.49
    adapters
    0.49
    gana
    0.48
    adapter
    0.47
    svc
    0.46
    POSITIVE LOGITS
     rét
    0.54
     copos
    0.51
     scène
    0.50
    沐
    0.47
     rằng
    0.45
     quilting
    0.45
     mixing
    0.45
     такі
    0.45
     sådan
    0.45
     Timm
    0.45
    Activations Density 0.000%

    No Known Activations