© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44007
    Prev
    Next
    INDEX
    Explanations

    ```pipeline checks```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     развитие
    0.49
    <0xA9>
    0.44
    ния
    0.44
     двига
    0.43
    stride
    0.42
    =(
    0.42
    ốc
    0.41
     nếu
    0.41
    udier
    0.40
     паз
    0.40
    POSITIVE LOGITS
    वण्यात
    0.57
     invaded
    0.49
     numbered
    0.47
    Prz
    0.47
     immort
    0.47
     Bitter
    0.47
    বেগ
    0.46
    امی
    0.46
    പ
    0.46
    انس
    0.46
    Activations Density 0.002%

    No Known Activations