© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9852
    Prev
    Next
    INDEX
    Explanations

    solving linear systems

    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_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
     cake
    0.42
     Cake
    0.42
    🎂
    0.39
     viaggi
    0.36
     फार्मूला
    0.35
    languageTag
    0.35
     rollout
    0.35
     कौशिक
    0.35
    펼
    0.34
     reunited
    0.34
    POSITIVE LOGITS
     elimination
    1.07
     Elimination
    0.97
     elimin
    0.83
    Elim
    0.80
     eliminación
    0.80
     Eliminate
    0.78
     eliminated
    0.77
     sistema
    0.77
     Elimin
    0.77
     eliminate
    0.75
    Activations Density 0.152%

    No Known Activations