© 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-262K
    7. 5169
    Prev
    Next
    INDEX
    Explanations

    pastebin links

    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
     horr
    0.32
    स्परिक
    0.28
     castration
    0.27
     ochrony
    0.26
    らう
    0.26
     vacuo
    0.26
     murdering
    0.26
    佉
    0.26
     solucionar
    0.26
     Versorgung
    0.26
    POSITIVE LOGITS
    _
    0.36
    -
    0.34
    peek
    0.33
    0.33
    un
    0.32
    ay
    0.32
    yn
    0.31
     [
    0.31
    ↵
    0.31
    current
    0.31
    Activations Density 0.068%

    No Known Activations