© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13746
    Prev
    Next
    INDEX
    Explanations

    undetectable subtle changes

    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_40_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
     demanded
    0.41
     motivated
    0.38
     яр
    0.36
     vouloir
    0.36
     definitiv
    0.35
    鞦
    0.35
    ますが
    0.35
    emph
    0.35
     겁
    0.34
     ആവശ
    0.34
    POSITIVE LOGITS
     unnoticed
    2.36
     invisible
    2.28
     hidden
    2.27
     secretly
    2.16
    invisible
    2.09
     undetected
    2.06
     invis
    2.03
     unseen
    2.03
    hidden
    2.00
    Invisible
    2.00
    Activations Density 0.057%

    No Known Activations