© 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. 132772
    Prev
    Next
    INDEX
    Explanations

    divine providence, Joshua, love

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

    thinking about what's next

    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
     "?
    0.47
    回来了
    0.46
     >
    0.45
     offerte
    0.44
    巴巴
    0.44
    不说
    0.43
     inconn
    0.42
    quele
    0.42
    quela
    0.42
     заинтере
    0.41
    POSITIVE LOGITS
    čních
    0.49
     कृष्णा
    0.48
    ческих
    0.47
    plates
    0.47
     さらに
    0.45
     वैज्ञानिकों
    0.45
    firetruck
    0.44
    ᵚ
    0.44
     Persians
    0.43
    iches
    0.43
    Activations Density 0.001%

    No Known Activations