© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69990
    Prev
    Next
    INDEX
    Explanations

    more of something

    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
    heds
    -1.20
     помогают
    -1.20
    Processes
    -1.13
    othes
    -1.09
     سایر
    -1.09
     THOSE
    -1.06
     autres
    -1.05
    嘴唇
    -1.04
    discussed
    -1.02
     gän
    -1.02
    POSITIVE LOGITS
     than
    3.23
     of
    3.16
     like
    1.42
     from
    1.39
     importantly
    1.38
    than
    1.20
     {
    1.18
     to
    1.12
     besides
    1.09
     nữa
    1.07
    Activations Density 0.030%

    No Known Activations