© 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. 186606
    Prev
    Next
    INDEX
    Explanations

    MLC Regulations

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

    alternating blocks

    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
    痞
    0.50
    轨迹
    0.48
     ठिकाणी
    0.47
     ০
    0.47
     மூன்றாவது
    0.46
    Barnes
    0.46
     ظِلِّ
    0.45
    第三
    0.45
    িনবার্গ
    0.45
    MaxIntensity
    0.44
    POSITIVE LOGITS
     mass
    0.52
     valuation
    0.51
     asset
    0.47
     superpower
    0.47
    produkt
    0.46
    /
    0.46
    *
    0.45
     besuchte
    0.45
     migrants
    0.45
     d
    0.44
    Activations Density 0.000%

    No Known Activations