© 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. 159242
    Prev
    Next
    INDEX
    Explanations

    categories and topics

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

    Morphic Resonance Sheldrake operating systems

    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
    ৯
    0.58
     Deshalb
    0.52
    mittedly
    0.48
     نقل
    0.47
     woh
    0.47
     اريد
    0.47
     Пока
    0.46
     schne
    0.46
    र्में
    0.45
     mein
    0.45
    POSITIVE LOGITS
     जनवरी
    0.49
    oS
    0.46
     соору
    0.45
    栏
    0.43
     বৎসর
    0.42
     checkered
    0.42
    caches
    0.42
    密钥
    0.42
    πάν
    0.41
     ምስ
    0.41
    Activations Density 0.000%

    No Known Activations