© 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. 51282
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    斯
    0.50
    0.44
     मैने
    0.44
     wären
    0.44
     annealing
    0.42
    стром
    0.42
    σιν
    0.42
     执行
    0.41
     ausgeführt
    0.41
    冒
    0.41
    POSITIVE LOGITS
     on
    0.47
     monthly
    0.43
     dermat
    0.42
     वीरता
    0.42
     squadron
    0.42
    rzost
    0.42
    公主
    0.41
    Agricult
    0.40
     palp
    0.40
     princesses
    0.40
    Activations Density 0.015%

    No Known Activations