© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10977
    Prev
    Next
    INDEX
    Explanations

    whether ... or

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

    technical descriptions and instructions

    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_40_width_16k_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
    ర్స్
    0.30
     Thời
    0.27
     аутох
    0.27
    <unused2157>
    0.26
     動物
    0.25
    画家
    0.25
     热
    0.25
     让
    0.25
    τές
    0.25
     方法
    0.24
    POSITIVE LOGITS
     menacing
    0.28
     domine
    0.28
    pesar
    0.27
     despise
    0.27
     interne
    0.26
     infliction
    0.26
     betrayal
    0.26
     zada
    0.26
     inflict
    0.26
    reli
    0.25
    Activations Density 0.635%

    No Known Activations