© 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. 173571
    Prev
    Next
    INDEX
    Explanations

    statesmen or condition

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

    geographical locations and specific entities

    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
    JX
    0.52
    EJ
    0.45
    ਝ
    0.45
    僵
    0.44
     మాట్లాడుతూ
    0.42
    Zi
    0.42
     oxidize
    0.42
    曱
    0.42
    HEMAT
    0.41
    م
    0.41
    POSITIVE LOGITS
     Và
    0.55
     Family
    0.52
     Vatican
    0.50
     Museu
    0.49
     Vatic
    0.48
    ຫານ
    0.46
    観光
    0.46
     Tú
    0.46
     Eat
    0.46
    hspace
    0.45
    Activations Density 0.000%

    No Known Activations