© 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. 175403
    Prev
    Next
    INDEX
    Explanations

    sales page, message, cleaning agent, sponsorship, good platform

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

    health and financial terms

    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
     Juga
    0.49
    尕
    0.46
     Mejor
    0.45
    レア
    0.45
     stoi
    0.45
    最高の
    0.44
     Ekim
    0.42
    立ち
    0.42
    จะต้อง
    0.42
     समझिए
    0.41
    POSITIVE LOGITS
     抗
    0.53
    قتها
    0.52
    heme
    0.47
    anced
    0.47
    idemargin
    0.47
    الأ
    0.46
    حية
    0.46
    نين
    0.45
    eta
    0.45
    voj
    0.45
    Activations Density 0.002%

    No Known Activations