© 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. 179280
    Prev
    Next
    INDEX
    Explanations

    subcommittee, contest, projects, controls, home, also

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

    Princess Lily, King Elon

    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
    不可以
    0.49
    刺
    0.44
    定番
    0.43
    ''
    0.43
    IMP
    0.41
    و
    0.41
    IKA
    0.40
    为了
    0.40
    δά
    0.40
    <0xBA>
    0.40
    POSITIVE LOGITS
    ಿಂದ
    0.53
     नेतृत्व
    0.53
     ভোট
    0.48
     kilka
    0.47
     قیادت
    0.47
    forschung
    0.47
     contribu
    0.46
     chiq
    0.46
    ">→</
    0.46
    হিত
    0.45
    Activations Density 0.001%

    No Known Activations