© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97908
    Prev
    Next
    INDEX
    Explanations

    IT professionals and companies

    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
     whilst
    -1.75
    Whilst
    -1.56
     Whilst
    -1.53
     our
    -1.42
    更に
    -1.38
     Amongst
    -1.20
     चीज़
    -1.16
     amongst
    -1.15
     através
    -1.13
    非常的
    -1.12
    POSITIVE LOGITS
     Assn
    1.20
     Ancak
    1.20
     staffers
    1.12
     etwa
    1.09
     нынеш
    1.07
    いえば
    1.02
     temb
    1.01
     environs
    1.01
     nab
    0.97
    いい
    0.97
    Activations Density 0.164%

    No Known Activations