© 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. 37389
    Prev
    Next
    INDEX
    Explanations

    Holy Spirit of promise

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

    "I'll" followed by explanations

    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
     ア
    0.54
     リ
    0.49
     drape
    0.49
     セ
    0.49
     በቀ
    0.49
     ቲ
    0.48
     カル
    0.46
     intrigue
    0.46
     curt
    0.46
     ハ
    0.45
    POSITIVE LOGITS
    emes
    0.63
    emos
    0.52
    en
    0.50
     situaciones
    0.49
    माटर
    0.48
    grit
    0.48
    蜢
    0.48
    mix
    0.47
    odor
    0.47
    inspir
    0.47
    Activations Density 0.000%

    No Known Activations