© 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. 175347
    Prev
    Next
    INDEX
    Explanations

    resource entries

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

    relationship dynamics and attention

    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
    ᅯ
    0.52
    .'),
    0.49
     раздела
    0.48
     pertenec
    0.47
     AppBsky
    0.47
     неред
    0.47
    postas
    0.46
     bevat
    0.45
    >′
    0.45
    রদ্ব
    0.45
    POSITIVE LOGITS
    lık
    0.56
    这
    0.50
     elem
    0.49
    اك
    0.48
     Called
    0.47
    心态
    0.47
    這個
    0.46
    다
    0.46
    这个
    0.46
    指导
    0.46
    Activations Density 0.000%

    No Known Activations