© 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. 161384
    Prev
    Next
    INDEX
    Explanations

    between projects

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

    needs, air, cells, 1

    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
     фир
    0.48
     quê
    0.48
    riv
    0.47
     информа
    0.45
    sız
    0.44
     À
    0.43
     (.)
    0.43
    🇮
    0.43
    mét
    0.42
     നേരി
    0.42
    POSITIVE LOGITS
    饅
    0.47
    CTION
    0.46
    위
    0.46
    اني
    0.45
    WHEN
    0.45
    헹
    0.45
    स्वास्थ्य
    0.45
    कल
    0.44
    CellValue
    0.44
     labourers
    0.44
    Activations Density 0.001%

    No Known Activations