© 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. 124482
    Prev
    Next
    INDEX
    Explanations

    feedback about

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

    how, oxygen, integer

    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
    缛
    0.42
    ר
    0.41
    distanceArray
    0.41
    ุ
    0.41
    ᄌ
    0.40
    라도
    0.39
    anakk
    0.39
    지가
    0.38
    indahkan
    0.38
    迢
    0.38
    POSITIVE LOGITS
     signé
    0.45
    :
    0.45
     você
    0.44
    由
    0.42
     gxh
    0.42
     gemäß
    0.41
     dzięki
    0.40
     juice
    0.40
     prenda
    0.40
     servidor
    0.39
    Activations Density 0.003%

    No Known Activations