© 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. 106535
    Prev
    Next
    INDEX
    Explanations

    system reflection

    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
    𝔩
    -0.77
     hafif
    -0.72
    散
    -0.71
    
    -0.71
    凡
    -0.69
     следующем
    -0.68
    ђе
    -0.67
    ouvoir
    -0.66
    devším
    -0.66
    hombres
    -0.66
    POSITIVE LOGITS
    Inv
    0.77
     Chin
    0.73
     Fron
    0.71
    えている
    0.70
    JB
    0.68
     Islands
    0.67
     Alemanha
    0.66
     Individuals
    0.65
    Xna
    0.65
     JB
    0.64
    Activations Density 0.073%

    No Known Activations