© 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. 19549
    Prev
    Next
    INDEX
    Explanations

    warranties or condition

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

    disclaimers and conditions

    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
     দ্বীপ
    0.43
    omo
    0.41
    ológicas
    0.40
    Usuario
    0.40
    ornado
    0.39
    极为
    0.39
    <td>
    0.39
     содержит
    0.38
    ⌥
    0.38
    跟随
    0.38
    POSITIVE LOGITS
     garanti
    0.48
     garant
    0.47
     guarantees
    0.46
     garantías
    0.45
     assurances
    0.44
     warranties
    0.43
     ওয়ার
    0.42
     guarantee
    0.41
     warranty
    0.41
     liabilities
    0.41
    Activations Density 0.001%

    No Known Activations