© 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. 188513
    Prev
    Next
    INDEX
    Explanations

    romp along

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

    sugar control

    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
     gehören
    0.52
     gehör
    0.51
     består
    0.51
     黃
    0.48
     bä
    0.47
    ającej
    0.47
    ären
    0.47
     أص
    0.47
     संचाल
    0.46
     abz
    0.46
    POSITIVE LOGITS
    LayoutParams
    0.46
     robbers
    0.45
    jvm
    0.45
     humanities
    0.42
     murdering
    0.42
    𒁍
    0.42
    Nak
    0.42
    unable
    0.42
    onOptions
    0.42
    НА
    0.42
    Activations Density 0.002%

    No Known Activations