© 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. 36420
    Prev
    Next
    INDEX
    Explanations

    scientific rates and systems

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

    technological or economic processes

    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
    雱
    0.51
     бю
    0.46
     रकम
    0.45
     дни
    0.42
     оказыва
    0.41
    锒
    0.40
    ர்
    0.39
     বৈঠকে
    0.39
     нәрсә
    0.39
     bò
    0.38
    POSITIVE LOGITS
     mitochond
    0.51
    ecological
    0.48
     interdiscipl
    0.47
    assertion
    0.47
    生態
    0.47
    CHAIN
    0.46
    O
    0.46
     mitochondria
    0.45
    isection
    0.45
     biological
    0.45
    Activations Density 0.000%

    No Known Activations