© 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. 883
    Prev
    Next
    INDEX
    Explanations

    store store credit card parts necklaces

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

    storing information

    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
     رياض
    0.44
    開
    0.44
    踉
    0.43
    льності
    0.43
    兟
    0.43
     Pá
    0.42
    輸出
    0.42
    剛
    0.41
    ادي
    0.41
    يني
    0.41
    POSITIVE LOGITS
     저장
    1.33
     storage
    1.20
     storing
    1.13
     almacenamiento
    1.13
     ذخ
    1.10
     armazenamento
    1.05
     almacen
    1.04
     хранения
    1.04
     penyimpanan
    1.04
     przechowy
    1.03
    Activations Density 0.082%

    No Known Activations