© 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. 78397
    Prev
    Next
    INDEX
    Explanations

    igneous and underground sources

    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
    Dimensões
    -0.79
     torino
    -0.77
    Saiba
    -0.71
     duelo
    -0.71
    capacidad
    -0.70
     ось
    -0.70
    上で
    -0.69
     SOLO
    -0.69
     solos
    -0.68
    ないけど
    -0.68
    POSITIVE LOGITS
     intrusion
    1.45
     intrusive
    1.33
     mag
    1.28
     magma
    1.19
     volcanic
    1.14
     intrusions
    1.13
     Intru
    1.10
    trusive
    1.03
     feeder
    0.94
     המא
    0.93
    Activations Density 0.013%

    No Known Activations