© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131718
    Prev
    Next
    INDEX
    Explanations

    nearby exploding stars

    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_40_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
     শীতল
    0.46
     الحر
    0.45
     clothing
    0.42
     portable
    0.40
     placés
    0.38
    蟻
    0.38
     outs
    0.38
    熱
    0.38
     поса
    0.37
     slowly
    0.37
    POSITIVE LOGITS
     supernova
    1.01
     supernovae
    1.00
     explosion
    0.83
    爆炸
    0.79
    explosion
    0.76
    SN
    0.72
     explosions
    0.70
     Explosion
    0.70
     exploding
    0.68
     SN
    0.68
    Activations Density 0.011%

    No Known Activations