© 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. 54733
    Prev
    Next
    INDEX
    Explanations

    fees, registration, manner, first, tilt

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

    hormone bioavailability

    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
    <0xE3>
    0.53
    "
    0.48
     chest
    0.46
    د
    0.45
     receive
    0.43
    {
    0.43
     severe
    0.43
     sort
    0.43
    、
    0.43
    ط
    0.42
    POSITIVE LOGITS
     Pendleton
    0.48
     datth
    0.47
     لنک
    0.47
     reposition
    0.46
     कार्यकर्
    0.46
     alcoved
    0.46
    வர்களாக
    0.46
     ছাউ
    0.46
     DEX
    0.46
     ورلڈ
    0.46
    Activations Density 0.000%

    No Known Activations