© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8811
    Prev
    Next
    INDEX
    Explanations

    hiding or concealing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     Millet
    0.53
     Sway
    0.53
     NRG
    0.53
    клика
    0.52
     stranded
    0.52
     Ewing
    0.51
     validates
    0.50
    醪
    0.49
     Eminent
    0.49
    プション
    0.48
    POSITIVE LOGITS
     concealment
    2.52
     hiding
    2.45
     conceal
    2.33
     concealing
    2.33
     hide
    2.28
    隐藏
    2.25
     concealed
    2.20
     stealth
    2.20
     hides
    2.19
     esconder
    2.16
    Activations Density 0.717%

    No Known Activations