© 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. 201684
    Prev
    Next
    INDEX
    Explanations

    work-actions: tags, jenkins

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

    best practices for structure and scale

    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
     fees
    0.56
     infrastructural
    0.55
     infrastructure
    0.53
     investments
    0.53
     vibrate
    0.53
     speed
    0.50
    િ
    0.50
     costs
    0.48
     fluctuations
    0.47
     already
    0.47
    POSITIVE LOGITS
    rét
    0.60
     División
    0.53
     río
    0.51
    构
    0.51
     Sé
    0.49
     Sebastián
    0.49
    média
    0.49
    læ
    0.49
     वेदा
    0.48
    áln
    0.48
    Activations Density 0.001%

    No Known Activations