© 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. 158110
    Prev
    Next
    INDEX
    Explanations

    limited or constrained views

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

    artificial intelligence limitations

    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
     сели
    0.40
     पंचायतों
    0.39
    開き
    0.39
    ភ្ជាប់
    0.38
    เคย
    0.37
    ダス
    0.37
    voegd
    0.37
     Ashes
    0.37
     कर्ज
    0.37
     бывшего
    0.37
    POSITIVE LOGITS
     artificial
    0.63
     constrained
    0.56
     limitada
    0.55
    artificial
    0.54
     nécessairement
    0.52
     مصنوعی
    0.51
     necessarily
    0.51
     standardised
    0.51
     compressed
    0.50
     constrain
    0.50
    Activations Density 0.219%

    No Known Activations