© 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. 78324
    Prev
    Next
    INDEX
    Explanations

    more recent or advanced

    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
    different
    -1.23
     diferente
    -1.16
     più
    -1.13
     sowohl
    -1.13
     différentes
    -1.05
    讶
    -1.05
     différents
    -1.03
    を
    -1.03
    しかも
    -1.02
    みてください
    -1.02
    POSITIVE LOGITS
     than
    2.28
     traditional
    1.43
     recently
    1.31
     Recently
    1.30
     recent
    1.27
     or
    1.27
     conventional
    1.22
    Recently
    1.17
     advanced
    1.12
    際には
    1.10
    Activations Density 0.069%

    No Known Activations