© 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. 106953
    Prev
    Next
    INDEX
    Explanations

    HTML input attributes

    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
     name
    -3.03
     Name
    -2.42
    Name
    -2.25
    name
    -2.23
     NAME
    -2.06
    NAME
    -2.00
    名称
    -1.88
    名前
    -1.79
     Namen
    -1.76
     names
    -1.73
    POSITIVE LOGITS
     value
    0.93
     id
    0.90
     dijual
    0.88
    𝗯
    0.77
    戦士
    0.76
    だからこそ
    0.73
    参り
    0.71
    êtres
    0.71
    ︶
    0.71
    予報
    0.70
    Activations Density 0.006%

    No Known Activations