© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    previous steps or turns

    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
     transaction
    0.49
     customized
    0.47
     diffusion
    0.46
     danach
    0.43
     customizing
    0.42
     extrusion
    0.42
     процес
    0.42
    𝔦
    0.42
     beter
    0.42
     customizable
    0.42
    POSITIVE LOGITS
    VIOUS
    0.44
    UJ
    0.42
     Rother
    0.41
    Previous
    0.40
     précédentes
    0.40
    entures
    0.39
    accum
    0.38
     duly
    0.38
    Carry
    0.38
    previous
    0.37
    Activations Density 0.001%

    No Known Activations