© 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. 3449
    Prev
    Next
    INDEX
    Explanations

    origins and publications

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

    AI disclaimers about advice

    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
     Schlüssel
    0.24
     খ্রিস্ট
    0.23
     Keys
    0.22
     Shang
    0.22
     جنب
    0.22
     Variability
    0.22
     বাধ্যতামূলক
    0.21
    🥹
    0.21
     œuvre
    0.21
     أنها
    0.21
    POSITIVE LOGITS
    ख्त
    0.27
    aine
    0.26
    ვალ
    0.25
    報道
    0.25
    нува
    0.25
    epen
    0.24
    ља
    0.24
    ंजे
    0.24
     フロント
    0.24
     republished
    0.24
    Activations Density 0.101%

    No Known Activations