© 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. 89229
    Prev
    Next
    INDEX
    Explanations

    barred owl, pastors who

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

    complexity and accuracy levels

    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
    였다
    0.52
    ປະກ
    0.48
    дина
    0.47
    པ
    0.46
    ｆ
    0.46
    ग
    0.45
    onimo
    0.45
    த
    0.45
    г
    0.45
    ᠴ
    0.44
    POSITIVE LOGITS
     basing
    0.51
     hybridization
    0.50
     randomization
    0.48
     randomize
    0.46
     randomized
    0.46
     biodegradation
    0.46
     asymmetries
    0.45
     triage
    0.44
     discontinue
    0.43
     pairs
    0.43
    Activations Density 0.017%

    No Known Activations