© 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. 133256
    Prev
    Next
    INDEX
    Explanations

    spendingsecurebookinglivefromvotes

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

    fall over

    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
     oben
    0.49
    빅
    0.47
     heb
    0.43
     há
    0.43
     അമ
    0.41
    瘾
    0.41
     автомобі
    0.41
    għ
    0.41
     جمه
    0.40
     وي
    0.40
    POSITIVE LOGITS
    entry
    0.55
    𝗶
    0.49
    処分
    0.48
    스럽
    0.48
    ब्द
    0.47
    ᱱ
    0.47
    <unused9>
    0.47
    count
    0.46
    वाने
    0.46
    paint
    0.46
    Activations Density 0.000%

    No Known Activations