© 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. 61971
    Prev
    Next
    INDEX
    Explanations

    describing concepts, details, or limitations

    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
     zigzag
    0.37
     shortcomings
    0.37
     heterogeneity
    0.37
    ㄺ
    0.36
    olymer
    0.36
     сег
    0.36
     calibrated
    0.35
     scr
    0.35
     atr
    0.35
     spotted
    0.34
    POSITIVE LOGITS
    ディオ
    0.47
     dhe
    0.46
     хора
    0.46
     autant
    0.45
    deling
    0.45
    沔
    0.44
    Calls
    0.43
     त्यांना
    0.43
    speople
    0.43
    ում
    0.42
    Activations Density 0.006%

    No Known Activations