© 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. 117023
    Prev
    Next
    INDEX
    Explanations

    code identifiers and definitions

    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
     requires
    -0.94
     }}=\
    -0.93
    })=\
    -0.93
    <!--
    -0.91
     digging
    -0.90
    Decre
    -0.90
    这是一
    -0.89
    ジェクト
    -0.88
    kelen
    -0.88
     tedious
    -0.87
    POSITIVE LOGITS
    一定会
    1.02
    urement
    1.01
    /.../
    0.98
    _
    0.96
     válto
    0.91
    ჻
    0.91
    這個
    0.89
    rrrrr
    0.87
     hô
    0.87
     کوچ
    0.85
    Activations Density 0.198%

    No Known Activations