© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127791
    Prev
    Next
    INDEX
    Explanations

    unreal or unexpected situations

    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
     excitations
    0.40
    CurrentUser
    0.39
    dfrac
    0.39
     разре
    0.39
     nettement
    0.39
     التيار
    0.38
    mee
    0.37
    ⢸
    0.37
     currentUser
    0.37
     सुचेता
    0.37
    POSITIVE LOGITS
    诈
    0.60
     hoax
    0.55
     fraud
    0.47
     mistake
    0.46
    奇怪
    0.46
     nuova
    0.45
     strange
    0.44
     counterfeit
    0.44
    詐
    0.44
     Accident
    0.44
    Activations Density 0.050%

    No Known Activations