© 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. 196736
    Prev
    Next
    INDEX
    Explanations

    currency and amounts

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

    friendly Lily Potter investigation

    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
    父
    0.48
    通用
    0.46
    宝宝
    0.44
    钥匙
    0.43
    陛下
    0.43
    保养
    0.43
    𝙥
    0.42
    包装
    0.42
    茥
    0.42
    𝒂
    0.42
    POSITIVE LOGITS
     fueron
    0.47
    0.46
     ലഭ
    0.46
     obtenue
    0.45
     quedaron
    0.45
     fi
    0.44
     investigation
    0.43
     obtenu
    0.42
     verksam
    0.42
     Ç
    0.42
    Activations Density 0.001%

    No Known Activations