© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    copyright years and names

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

    software commands and code

    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
    古屋
    0.41
    낍
    0.41
    結局
    0.41
    دا
    0.40
    relser
    0.40
     بالوں
    0.40
    ربية
    0.40
    aniyati
    0.39
     biops
    0.39
     بقى
    0.39
    POSITIVE LOGITS
    </strong>
    0.45
     Kubernetes
    0.42
     мати
    0.41
     മറ്റ്
    0.41
     Leonardo
    0.41
     Kud
    0.40
     Yves
    0.40
    ~$
    0.39
     Carlos
    0.38
     Gustavo
    0.38
    Activations Density 0.000%

    No Known Activations