© 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. 22-GEMMASCOPE-RES-131K
    7. 129301
    Prev
    Next
    INDEX
    Explanations

    methods, procedures, software

    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
     first
    -1.31
     initiating
    -1.20
    誣
    -1.18
     on
    -1.09
    izace
    -1.09
     immediately
    -1.08
     two
    -1.06
     three
    -1.04
     before
    -1.03
     spiaggia
    -1.03
    POSITIVE LOGITS
     software
    1.54
    Its
    1.33
    method
    1.28
    tools
    1.26
     user
    1.25
    Users
    1.23
     users
    1.20
    usually
    1.20
     usage
    1.20
     convenient
    1.16
    Activations Density 0.051%

    No Known Activations