© 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. 31-GEMMASCOPE-2-RES-65K
    7. 46025
    Prev
    Next
    INDEX
    Explanations

    currently / now

    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_65k_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
    扦
    0.40
     fauna
    0.38
     obscures
    0.37
     annoyance
    0.36
     phenomena
    0.35
     shreds
    0.35
    📍
    0.35
    🦴
    0.35
     Wart
    0.35
     natures
    0.35
    POSITIVE LOGITS
    𒁹
    0.38
     essas
    0.37
    ientemente
    0.36
    ichtlich
    0.36
     Conselho
    0.36
     estavam
    0.36
     lakini
    0.35
     মন্ত্রিস
    0.35
     estaban
    0.35
    ới
    0.35
    Activations Density 0.002%

    No Known Activations