© 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. 15493
    Prev
    Next
    INDEX
    Explanations

    dedicated kitchen, auditor is

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

    iterative version

    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
    変わり
    0.45
    TA
    0.41
    ucchini
    0.40
    ")[
    0.40
    QK
    0.40
    )"><
    0.39
    目标的
    0.39
     hatte
    0.38
    ">)</
    0.38
     बदलने
    0.38
    POSITIVE LOGITS
     anses
    0.43
     notations
    0.43
     architectures
    0.42
     objections
    0.41
     topologies
    0.41
     enquiries
    0.40
     superst
    0.40
     Brigadier
    0.39
     sympathies
    0.39
     dô
    0.38
    Activations Density 0.000%

    No Known Activations