© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28610
    Prev
    Next
    INDEX
    Explanations

    risks and complications

    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
     Armada
    0.40
    浲
    0.40
    របស់យើង
    0.40
    ওয়া
    0.38
     зер
    0.38
    ρα
    0.37
    °.
    0.37
     größten
    0.37
    畩
    0.37
    ApiOperation
    0.37
    POSITIVE LOGITS
     त्यांची
    0.50
     lorsqu
    0.48
    assurer
    0.45
     bola
    0.45
    čkom
    0.44
    чні
    0.43
     kanilang
    0.43
     vaginal
    0.43
     esetben
    0.42
     selection
    0.42
    Activations Density 0.001%

    No Known Activations