© 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. 179279
    Prev
    Next
    INDEX
    Explanations

    Hebrews 5:1, bar soap

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

    start with the source

    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
     Aerial
    0.49
     alleging
    0.49
    暱
    0.48
    ഷണ
    0.48
    sorption
    0.48
    ття
    0.47
     ภาพ
    0.47
     AIAA
    0.46
    ቝ
    0.46
     Allgeme
    0.46
    POSITIVE LOGITS
    用
    0.48
    ليا
    0.46
    Trusted
    0.42
    U
    0.40
    Author
    0.40
     clones
    0.40
    igot
    0.40
    Vers
    0.40
    usepackage
    0.39
    Normalize
    0.39
    Activations Density 0.002%

    No Known Activations