© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135328
    Prev
    Next
    INDEX
    Explanations

    possession and related 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
    a
    0.57
    the
    0.56
    ü
    0.52
    cept
    0.48
    ați
    0.46
    time
    0.45
    empt
    0.45
    ā
    0.44
    ه
    0.44
    か
    0.44
    POSITIVE LOGITS
     akhir
    0.65
     poss
    0.54
     possesses
    0.48
     dokumen
    0.48
     possessed
    0.48
     pos
    0.48
     обладает
    0.46
     bantuan
    0.46
     kemungkinan
    0.46
     dingin
    0.45
    Activations Density 0.013%

    No Known Activations