© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31610
    Prev
    Next
    INDEX
    Explanations

    anymore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     belum
    -0.93
     سایر
    -0.88
     chưa
    -0.84
    hiva
    -0.83
     None
    -0.82
     kwanza
    -0.80
     combineReducers
    -0.79
    laub
    -0.79
     médec
    -0.77
    ductor
    -0.75
    POSITIVE LOGITS
     anymore
    8.56
     enää
    4.06
     nữa
    3.69
     artık
    3.23
    不再
    2.55
     lagi
    2.47
     any
    2.45
     ormai
    2.36
    もはや
    2.33
     دیگر
    2.23
    Activations Density 0.148%

    No Known Activations