© 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. 248563
    Prev
    Next
    INDEX
    Explanations

    housing and time

    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
     Powered
    0.46
    ations
    0.43
    mbH
    0.43
    ！！！
    0.43
    其他人
    0.41
    ...
    0.41
    রাষ্ট্র
    0.41
    ○○
    0.41
    Skull
    0.41
     powered
    0.40
    POSITIVE LOGITS
     ihe
    0.54
     ആദ്യ
    0.52
     dnes
    0.49
     dź
    0.49
     vandaag
    0.48
     இன்றைய
    0.48
    𒌅
    0.48
     primeiro
    0.46
    cargo
    0.46
     pierwszej
    0.46
    Activations Density 0.001%

    No Known Activations