© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112021
    Prev
    Next
    INDEX
    Explanations

    determining how it goes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Savings
    0.50
    }\}$
    0.46
    กับ
    0.46
    早已
    0.46
    啡
    0.45
    りと
    0.45
    分野
    0.45
    ด
    0.45
    블
    0.45
    与
    0.45
    POSITIVE LOGITS
     covalent
    0.49
     rework
    0.48
    નો
    0.48
     swept
    0.47
     ionizing
    0.47
     AAS
    0.46
     dichloromethane
    0.45
     filamentous
    0.45
     Wastewater
    0.45
     cautious
    0.45
    Activations Density 0.000%

    No Known Activations