© 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. 2245
    Prev
    Next
    INDEX
    Explanations

    caching mechanisms (FIFO, LRU)

    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
    ዎ
    -0.75
    Bett
    -0.71
     Pourquoi
    -0.71
    ★★★
    -0.69
     Grâce
    -0.68
    Cristina
    -0.68
     BLANK
    -0.68
     Betty
    -0.68
    ิจ
    -0.67
    국의
    -0.66
    POSITIVE LOGITS
     FIFO
    2.47
    FIFO
    2.28
    LR
    1.97
     MR
    1.84
     fifo
    1.79
     L
    1.70
    fifo
    1.67
    MR
    1.63
     LR
    1.49
    lru
    1.49
    Activations Density 0.066%

    No Known Activations