© 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-262K
    7. 10870
    Prev
    Next
    INDEX
    Explanations

    on edge, on mission, on grind

    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
    næ
    0.41
     conjunction
    0.36
    aju
    0.36
    ◀
    0.36
    ^_
    0.36
     què
    0.36
    /\
    0.35
    _^
    0.35
    /__
    0.35
    вів
    0.35
    POSITIVE LOGITS
     tenter
    0.59
     fumes
    0.55
     rollerskates
    0.54
     antibiotics
    0.51
     payroll
    0.51
     alert
    0.49
     antidepressants
    0.46
     dialysis
    0.45
    rollerskates
    0.45
     skates
    0.44
    Activations Density 0.009%

    No Known Activations