© 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. 126896
    Prev
    Next
    INDEX
    Explanations

    breach of trust or process

    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
    𝟖
    0.51
    та
    0.47
     гель
    0.45
    するために
    0.44
     Unterschiede
    0.44
     aument
    0.44
    де
    0.43
    кли
    0.43
    捶
    0.43
     punching
    0.43
    POSITIVE LOGITS
    veyor
    0.48
    Noto
    0.45
    vey
    0.44
    ophiles
    0.43
    plus
    0.43
    Vote
    0.43
    u
    0.43
    i
    0.42
    錡
    0.41
     template
    0.41
    Activations Density 0.001%

    No Known Activations