© 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. 22-GEMMASCOPE-RES-131K
    7. 33694
    Prev
    Next
    INDEX
    Explanations

    parent-child development and safety

    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
    Proven
    -0.95
    ೭
    -0.94
     ночи
    -0.93
     or
    -0.93
     iyo
    -0.92
    轻易
    -0.91
    Prove
    -0.90
    nal
    -0.90
    𝑅
    -0.90
     recientes
    -0.89
    POSITIVE LOGITS
     späteren
    1.49
     healthy
    1.35
     pozdě
    1.34
     später
    1.30
     kés
    1.27
    将来
    1.20
     christlichen
    1.17
     futuras
    1.14
    ığımız
    1.11
    长大
    1.11
    Activations Density 0.031%

    No Known Activations