© 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. 227761
    Prev
    Next
    INDEX
    Explanations

    this is/was

    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
     Rescue
    0.50
    ”
    0.47
     لكن
    0.47
    Block
    0.46
    Limits
    0.45
    But
    0.45
    Remove
    0.44
     City
    0.43
    Rescue
    0.43
    ↵
    0.43
    POSITIVE LOGITS
    ্া
    0.55
    䨪
    0.54
    𓐄
    0.52
    裵
    0.52
    銥
    0.50
     RECEIVED
    0.50
     tubules
    0.49
    MISSION
    0.48
     cPix
    0.48
     experimentado
    0.48
    Activations Density 0.000%

    No Known Activations