© 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. 226187
    Prev
    Next
    INDEX
    Explanations

    origins of concepts

    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
     デ
    0.50
     المُ
    0.46
    ḗ
    0.46
     dement
    0.46
     レ
    0.46
    inence
    0.46
    だけでなく
    0.46
    Classifier
    0.45
    簟
    0.45
     महारा
    0.45
    POSITIVE LOGITS
     inventors
    0.47
    一支
    0.42
    sourceforge
    0.42
    网友
    0.41
    sometimes
    0.40
    la
    0.40
    роди
    0.40
     brainchild
    0.40
    htm
    0.40
     perpetuity
    0.40
    Activations Density 0.000%

    No Known Activations