© 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. 97173
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize winners

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

    Nobel prize winner

    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
    促销
    0.49
     এয়ার
    0.48
    彥
    0.47
    坟
    0.45
     wygl
    0.45
    ᔾ
    0.45
    欳
    0.44
     bumps
    0.44
    슭
    0.44
    ༥
    0.43
    POSITIVE LOGITS
     Nobel
    1.05
    Nob
    0.77
     Swedish
    0.63
    Swedish
    0.60
     nob
    0.58
    nob
    0.55
     awarding
    0.55
     laureate
    0.53
     Nob
    0.52
     awarded
    0.52
    Activations Density 0.022%

    No Known Activations