© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49410
    Prev
    Next
    INDEX
    Explanations

    what to do or expect

    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
    oluble
    -1.13
    iferous
    -1.09
    erson
    -1.09
    alties
    -1.07
    RemindMe
    -1.01
    ffect
    -1.01
    ulence
    -1.00
     corporativa
    -1.00
    ôs
    -0.98
     Olympedia
    -0.98
    POSITIVE LOGITS
     expect
    2.42
    expect
    1.80
     Expect
    1.45
    Expect
    1.43
     use
    1.26
     expects
    1.21
     expected
    1.20
     include
    1.15
     look
    1.15
    EXPECT
    1.13
    Activations Density 0.025%

    No Known Activations