© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2817
    Prev
    Next
    INDEX
    Explanations

    baseball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    li
    1.21
    organiser
    1.17
     آپ
    1.12
     Murt
    1.07
    ö
    1.05
     learnt
    1.05
     слід
    1.04
    パーティ
    1.04
     ترکیه
    1.03
     timescale
    1.03
    POSITIVE LOGITS
     baseball
    2.33
    Baseball
    2.29
     Baseball
    2.25
    baseball
    2.21
     MLB
    2.03
    MLB
    1.98
    ⚾
    1.92
     softball
    1.82
     pitcher
    1.79
     pitchers
    1.75
    Activations Density 0.019%

    No Known Activations