© 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. 152133
    Prev
    Next
    INDEX
    Explanations

    traditional rulers, year awards

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

    technical issues and connectivity

    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
    Getty
    0.44
    roquois
    0.42
    闱
    0.41
    Housing
    0.40
    ⚠️
    0.40
    Female
    0.39
    Sensitivity
    0.39
     Trebuie
    0.39
    ET
    0.38
     اصلي
    0.38
    POSITIVE LOGITS
    diği
    0.46
    ির
    0.45
     হাঁ
    0.45
    collectibles
    0.45
     musicals
    0.43
     heirloom
    0.43
     যাই
    0.43
    ᱖
    0.43
     ព
    0.42
     consonant
    0.42
    Activations Density 0.001%

    No Known Activations