© 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. 101992
    Prev
    Next
    INDEX
    Explanations

    pay or money, insurance, family, rise

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

    list explanations

    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
    ivanja
    0.55
     मल्टीप्लिकेशन
    0.50
     케
    0.50
    栥
    0.50
    ība
    0.49
    觓
    0.49
    㑬
    0.49
    㬹
    0.49
    <unused24>
    0.48
    ackel
    0.47
    POSITIVE LOGITS
    @
    0.51
    "
    0.49
    Ow
    0.48
    A
    0.47
    D
    0.47
    E
    0.46
    AY
    0.46
    ”
    0.46
    NY
    0.45
    +(-
    0.45
    Activations Density 0.001%

    No Known Activations