© 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. 218599
    Prev
    Next
    INDEX
    Explanations

    actions and information

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

    always been or had

    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
     ग्रे
    0.51
     ។
    0.51
     klare
    0.50
     แม
    0.49
     thom
    0.49
    僉
    0.47
     सबसे
    0.47
     Phó
    0.46
     ใช้
    0.46
     അ
    0.46
    POSITIVE LOGITS
    ILD
    0.46
    DH
    0.45
    biotic
    0.43
    🧠
    0.42
    '+
    0.41
    set
    0.40
    t
    0.40
    Yep
    0.40
    trigger
    0.40
    ☘
    0.40
    Activations Density 0.000%

    No Known Activations