© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66257
    Prev
    Next
    INDEX
    Explanations

    something went wrong

    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
     poud
    -1.20
    鱨
    -1.18
     stadion
    -1.17
     minimalis
    -1.13
     チラ
    -1.12
     filmp
    -1.11
     trak
    -1.09
    doing
    -1.09
     kanton
    -1.09
     作り方
    -1.09
    POSITIVE LOGITS
     happened
    2.16
     went
    1.64
     like
    1.59
     else
    1.58
     has
    1.55
     is
    1.55
     had
    1.51
     about
    1.50
     changed
    1.47
     terrible
    1.45
    Activations Density 0.019%

    No Known Activations