© 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. 96088
    Prev
    Next
    INDEX
    Explanations

    legal extent permitted

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

    air / divergence

    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
    ட்டிக்
    0.46
     निष्
    0.42
     Supply
    0.42
    艱
    0.41
    Supply
    0.40
     یقین
    0.40
     Softball
    0.40
     Rash
    0.40
     നേടിയ
    0.40
    esinde
    0.39
    POSITIVE LOGITS
     autour
    0.48
     বিহার
    0.47
    下午
    0.47
    唢
    0.43
    底部
    0.43
    chave
    0.43
    背面
    0.43
    ローラ
    0.43
     :::
    0.42
    火
    0.42
    Activations Density 0.002%

    No Known Activations