© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31284
    Prev
    Next
    INDEX
    Explanations

    technical terms and their attributes

    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
     vielleicht
    -1.31
    perhaps
    -1.22
    THERE
    -1.13
     mungkin
    -1.13
    looked
    -1.10
    sometimes
    -1.09
    噘
    -1.07
     Vielleicht
    -1.05
    
    -1.05
    might
    -1.04
    POSITIVE LOGITS
     by
    1.30
     of
    1.25
     in
    1.21
     for
    1.13
     focused
    1.12
     focusing
    1.05
     which
    1.05
     at
    1.04
     not
    1.02
     as
    1.02
    Activations Density 0.309%

    No Known Activations