© 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. 80513
    Prev
    Next
    INDEX
    Explanations

    accounts from God

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

    mathematical, computational, or explanatory processes

    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
    .‏
    0.51
     Taf
    0.48
    𝘀
    0.45
     जिनसे
    0.44
     ܕ
    0.43
    ]".
    0.43
     Martín
    0.43
    ".[
    0.42
    тков
    0.42
    eson
    0.42
    POSITIVE LOGITS
    InputStream
    0.46
     német
    0.45
    Ingredient
    0.45
    Cleaning
    0.44
    جمة
    0.44
     mathematical
    0.43
     haunt
    0.43
     infusion
    0.43
    лення
    0.43
    Definition
    0.42
    Activations Density 0.000%

    No Known Activations