© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15447
    Prev
    Next
    INDEX
    Explanations

    law of the case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …
    -2.33
    にしても
    -2.23
     […]
    -2.23
    鼙
    -2.20
    vantaged
    -2.13
    ㄍ
    -2.03
    每一次
    -2.00
     —
    -2.00
     จาก
    -1.97
    which
    -1.96
    POSITIVE LOGITS
    mathrm
    2.58
    我
    2.47
    你
    2.38
    在
    2.33
     сказала
    2.33
    玬
    2.30
    ϟ
    2.27
    }$
    2.25
    但
    2.22
     atau
    2.17
    Activations Density 0.026%

    No Known Activations