© 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. 78416
    Prev
    Next
    INDEX
    Explanations

    #include, Rangers, Monday, Your

    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
     for
    -1.09
     while
    -1.07
     both
    -1.05
     one
    -1.03
     three
    -1.02
     first
    -0.99
     an
    -0.97
     six
    -0.96
     two
    -0.89
     had
    -0.88
    POSITIVE LOGITS
     unending
    1.05
     grotes
    1.02
     relentless
    0.94
    },
    0.94
     finn
    0.93
     quadrinhos
    0.93
     Alkohol
    0.93
    薄い
    0.90
    ,”
    0.90
     bologna
    0.90
    Activations Density 0.000%

    No Known Activations