© 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. 63669
    Prev
    Next
    INDEX
    Explanations

    inserting into sequences

    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
    шений
    -0.86
    Ecuador
    -0.85
     insertion
    -0.84
     natura
    -0.82
     inser
    -0.82
    inserted
    -0.81
    inser
    -0.81
     inserted
    -0.79
     insertions
    -0.78
    halb
    -0.77
    POSITIVE LOGITS
     at
    1.08
    
    0.75
     into
    0.74
    灘
    0.74
    против
    0.72
     elástica
    0.70
    vesh
    0.68
     macrophage
    0.67
    violation
    0.67
    剐
    0.67
    Activations Density 0.043%

    No Known Activations