© 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. 128854
    Prev
    Next
    INDEX
    Explanations

    combining two or more things

    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
    з
    -0.92
    ppings
    -0.87
     in
    -0.86
    w
    -0.85
     бампер
    -0.84
     транспор
    -0.84
    etc
    -0.84
    ]
    -0.83
    ded
    -0.83
    or
    -0.83
    POSITIVE LOGITS
     and
    1.52
     both
    1.43
    ทั้ง
    1.41
     både
    1.41
    both
    1.24
     zarówno
    1.16
     keduanya
    1.14
     zowel
    1.10
     beiden
    1.10
    Both
    1.10
    Activations Density 0.115%

    No Known Activations