© 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. 22-GEMMASCOPE-RES-131K
    7. 13988
    Prev
    Next
    INDEX
    Explanations

    system calls, technical terms

    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_22/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
    좀
    -1.02
     with
    -1.00
    quela
    -0.93
     тех
    -0.93
     plus
    -0.93
    镰
    -0.91
    白眼
    -0.91
    ANDOM
    -0.91
    Эзоҳ
    -0.91
     Other
    -0.89
    POSITIVE LOGITS
    ؛
    1.00
     саны
    0.98
     Paco
    0.93
    因为
    0.92
    continence
    0.92
     gesagt
    0.87
    $;
    0.86
    因為
    0.84
    伊朗
    0.84
    ício
    0.84
    Activations Density 0.001%

    No Known Activations