© 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. 6594
    Prev
    Next
    INDEX
    Explanations

    secretly wronged or useless

    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
    鲔
    0.53
    髖
    0.49
    鈮
    0.48
    煐
    0.47
     фараз
    0.46
     esimerk
    0.46
     structuring
    0.45
    莴
    0.45
    鳟
    0.45
    矵
    0.44
    POSITIVE LOGITS
     blackmail
    0.49
     secretly
    0.48
    ji
    0.48
     wronged
    0.46
     useless
    0.44
     stupid
    0.44
     hehe
    0.43
    hehe
    0.43
     pretended
    0.43
     traitor
    0.43
    Activations Density 0.005%

    No Known Activations