© 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. 31-GEMMASCOPE-2-RES-262K
    7. 20334
    Prev
    Next
    INDEX
    Explanations

    suspicious character named

    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
     and
    0.50
     +
    0.43
     &
    0.40
    2
    0.38
     .
    0.38
     x
    0.38
     $
    0.36
    x
    0.36
    和
    0.36
    ,
    0.35
    POSITIVE LOGITS
     sobbing
    0.40
     Fiscalía
    0.34
     policías
    0.31
    ómago
    0.31
     Timurtaş
    0.29
     astonished
    0.29
     horrified
    0.29
     traumat
    0.29
     appalled
    0.28
     disgraceful
    0.28
    Activations Density 7.297%

    No Known Activations