© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 527
    Prev
    Next
    INDEX
    Explanations

    Awakenings! BIG MEET Made Shop FORM body

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

    Reboot Nation, Fortify Program

    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
     dictum
    0.26
    tedir
    0.24
     hehe
    0.23
     Göttingen
    0.23
    diagnostic
    0.23
    disable
    0.22
     hinsichtlich
    0.22
     },
    0.22
     geometrical
    0.22
    termination
    0.22
    POSITIVE LOGITS
     Series
    0.28
     Coalition
    0.28
     Lounge
    0.28
     Champions
    0.27
    ™
    0.27
     Parenting
    0.26
     Lifestyle
    0.26
    лії
    0.26
    κό
    0.26
    シリーズ
    0.26
    Activations Density 1.134%

    No Known Activations