© 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. 29476
    Prev
    Next
    INDEX
    Explanations

    explanation, application, definition

    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
    ikke
    0.49
    uisce
    0.48
     संधी
    0.48
    riko
    0.47
    raintes
    0.47
    غن
    0.47
    та
    0.47
    á
    0.47
    izmus
    0.46
    竅
    0.46
    POSITIVE LOGITS
     Sut
    0.44
     Proced
    0.44
    ົມ
    0.44
    UnderTest
    0.43
     Contribution
    0.43
     Serm
    0.43
     Frontend
    0.42
     Geometry
    0.42
     Usage
    0.42
    版的
    0.42
    Activations Density 0.002%

    No Known Activations