© 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. 48614
    Prev
    Next
    INDEX
    Explanations

    terms of the

    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
     (
    -1.27
    漁港
    -1.10
    つまり
    -1.02
     on
    -1.00
     quicker
    -0.97
     shivered
    -0.97
     лише
    -0.96
    Према
    -0.96
     mulighed
    -0.96
    っけ
    -0.96
    POSITIVE LOGITS
     and
    1.48
     which
    1.35
     but
    1.30
     WHICH
    1.22
     οποία
    1.21
    cosis
    1.17
    so
    1.16
    并
    1.13
    割と
    1.13
    corrhi
    1.10
    Activations Density 0.154%

    No Known Activations