© 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. 192086
    Prev
    Next
    INDEX
    Explanations

    car or truck service

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

    generating story, holding assets, reasons for root

    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
     aparel
    0.58
     vostra
    0.57
     anda
    0.54
    rov
    0.51
     Apparatus
    0.50
     aparato
    0.50
     aparelho
    0.50
    )
    0.50
    ]
    0.49
     Examin
    0.49
    POSITIVE LOGITS
    สเตอร์
    0.49
    软
    0.49
    潵
    0.45
     platter
    0.45
    ตำแหน่ง
    0.44
    剧中
    0.43
     акций
    0.43
    텨
    0.43
    指定
    0.42
    뮌
    0.42
    Activations Density 0.000%

    No Known Activations