© 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. 83027
    Prev
    Next
    INDEX
    Explanations

    elected governor

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

    grilled cheese, dill pickle

    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
    nX
    0.50
    海道
    0.49
    XO
    0.49
    Rn
    0.49
    تب
    0.48
    խ
    0.48
    ृह
    0.48
    прия
    0.47
    эро
    0.47
    २
    0.47
    POSITIVE LOGITS
     think
    0.52
     ward
    0.52
     do
    0.52
     rite
    0.50
     biometric
    0.48
     white
    0.47
     suicide
    0.47
     string
    0.46
     punk
    0.45
     tra
    0.44
    Activations Density 0.001%

    No Known Activations