© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130153
    Prev
    Next
    INDEX
    Explanations

    continue or further

    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
    щал
    -1.13
    exceptions
    -1.05
     ennen
    -1.04
    tachten
    -1.00
    cześ
    -1.00
    ционер
    -0.97
    Diret
    -0.96
     siento
    -0.95
    czych
    -0.94
    ئه
    -0.94
    POSITIVE LOGITS
     further
    2.08
     continue
    1.66
     weitere
    1.60
     дальше
    1.59
    继续
    1.48
     continued
    1.41
    continue
    1.40
     pokrač
    1.40
    further
    1.38
     далее
    1.38
    Activations Density 0.049%

    No Known Activations