© 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. 91838
    Prev
    Next
    INDEX
    Explanations

    activities and workshops

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

    code snippets and structure

    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
     непотпуним
    0.52
     sincere
    0.45
    ળ
    0.44
     precum
    0.44
     speechless
    0.42
     dispuestos
    0.42
     parece
    0.42
     dispuesto
    0.41
     bernama
    0.41
     llamados
    0.41
    POSITIVE LOGITS
    oucher
    0.50
    ITI
    0.49
    nicy
    0.48
     ふ
    0.47
    nq
    0.46
    ulnerability
    0.46
    örü
    0.46
     下
    0.46
    奨
    0.45
    ಗ
    0.45
    Activations Density 0.000%

    No Known Activations