© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119275
    Prev
    Next
    INDEX
    Explanations

    created by

    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
    pielt
    -0.79
    ليف
    -0.79
     góp
    -0.76
    ⌝
    -0.73
    änge
    -0.72
    ullus
    -0.72
    SDAY
    -0.72
     assessor
    -0.71
    acamata
    -0.71
     qualific
    -0.70
    POSITIVE LOGITS
     OSI
    0.84
    ΤΗ
    0.78
     IDL
    0.77
    Archer
    0.74
    jetbrains
    0.73
     Schauspiel
    0.72
     宗
    0.72
    øg
    0.71
     Venture
    0.71
    Ban
    0.70
    Activations Density 0.016%

    No Known Activations