© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    splitting triangles

    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_16k_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
    Podcast
    0.49
     Podcast
    0.45
     Rigid
    0.45
    编
    0.42
    <h4>
    0.41
    WAT
    0.41
     Thurman
    0.41
     Dynamic
    0.41
     Psychic
    0.41
    స్తున్నారు
    0.40
    POSITIVE LOGITS
     restoration
    0.55
     embezzlement
    0.54
    ilized
    0.51
    깽
    0.50
     optimization
    0.49
     attains
    0.48
     pinching
    0.48
     recuper
    0.48
     reversion
    0.48
    collapse
    0.47
    Activations Density 0.118%

    No Known Activations