© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93351
    Prev
    Next
    INDEX
    Explanations

    SQL queries or data selection

    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
     verp
    -0.79
     sorteo
    -0.78
    کیل
    -0.78
    xed
    -0.77
    UserID
    -0.77
     GOD
    -0.76
    foil
    -0.76
     partout
    -0.76
     atrap
    -0.75
     coupable
    -0.75
    POSITIVE LOGITS
     where
    1.30
    Select
    1.07
     select
    0.99
    where
    0.98
    select
    0.96
     from
    0.93
     Select
    0.90
    肺
    0.90
    正月
    0.89
    选择
    0.86
    Activations Density 0.009%

    No Known Activations