© 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. 33682
    Prev
    Next
    INDEX
    Explanations

    however,

    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
     and
    -2.92
     البته
    -2.09
    ar
    -2.09
    N
    -1.97
    M
    -1.95
    E
    -1.92
    i
    -1.89
    рений
    -1.77
    }$.
    -1.76
     見え
    -1.70
    POSITIVE LOGITS
    橚
    2.31
    へ向
    1.87
     it
    1.81
     dinosaurio
    1.76
    様が
    1.73
    tuan
    1.73
    ,
    1.71
    
    1.71
     that
    1.69
     verdient
    1.69
    Activations Density 0.043%

    No Known Activations