© 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. 28533
    Prev
    Next
    INDEX
    Explanations

    pm times

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

    times and time zones

    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
    Ellipse
    0.40
     ellipsoid
    0.39
    oglobine
    0.39
    ELL
    0.39
    Supplement
    0.38
     symbolized
    0.38
     signified
    0.38
    楕
    0.37
    يقة
    0.37
    Feb
    0.37
    POSITIVE LOGITS
     unor
    0.46
     учас
    0.43
     participants
    0.43
     participant
    0.43
    participant
    0.42
     Frankfurt
    0.41
     participantes
    0.40
     collab
    0.40
     promot
    0.39
     uczest
    0.39
    Activations Density 0.007%

    No Known Activations