© 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. 71987
    Prev
    Next
    INDEX
    Explanations

    giving up and giving something

    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
     when
    -1.89
     is
    -1.38
     in
    -1.32
     if
    -1.25
     from
    -1.19
     during
    -1.19
     here
    -1.12
     despite
    -1.12
    性質
    -1.08
    などが
    -1.07
    POSITIVE LOGITS
    谞
    1.34
    Giving
    1.32
    Gives
    1.27
    蟜
    1.26
    šas
    1.26
    themselves
    1.24
     tirantes
    1.24
     себя
    1.21
    Give
    1.20
     cordones
    1.20
    Activations Density 0.030%

    No Known Activations