© 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. 40-GEMMASCOPE-2-RES-262K
    7. 221039
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases linking words

    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
     hurt
    0.42
     defraud
    0.41
     quienes
    0.40
     quits
    0.40
    ∑</
    0.39
    杆
    0.39
     tournée
    0.38
     primer
    0.37
     quien
    0.37
     fraude
    0.37
    POSITIVE LOGITS
    Pax
    0.41
     Participation
    0.39
    ία
    0.39
    Participation
    0.38
     परिणामस्वरूप
    0.37
     आस
    0.37
     फरक
    0.37
    㜿
    0.37
    eau
    0.37
     диф
    0.36
    Activations Density 0.001%

    No Known Activations