© 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. 19224
    Prev
    Next
    INDEX
    Explanations

    left behind or leftover

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

    directional, spatial, and descriptive terms

    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
     numero
    0.53
     duro
    0.50
     adapters
    0.49
     schools
    0.49
     herbivores
    0.47
     todas
    0.46
    自体
    0.46
    ט
    0.46
     tents
    0.45
     mentality
    0.45
    POSITIVE LOGITS
    しまう
    0.55
    amise
    0.51
    ರುವುದರಿಂದ
    0.51
     परिणामस्वरूप
    0.49
    することにより
    0.48
    これにより
    0.45
    することで
    0.45
     Consequently
    0.44
    するため
    0.44
    ப்பதால்
    0.44
    Activations Density 0.000%

    No Known Activations