© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99428
    Prev
    Next
    INDEX
    Explanations

    works and God's will

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

    what to work

    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
     entertained
    0.40
    ృష్
    0.40
     aplatis
    0.40
    蜷
    0.40
    कर्
    0.39
    captivity
    0.39
     kapal
    0.37
    كما
    0.37
    ﺋ
    0.37
     eyewitness
    0.36
    POSITIVE LOGITS
    ızı
    0.43
     Work
    0.42
     งาน
    0.42
     वर्क
    0.42
     হওয়ায়
    0.42
    works
    0.41
     பொரு
    0.41
    ework
    0.41
    ığını
    0.41
     рабочей
    0.41
    Activations Density 0.034%

    No Known Activations