© 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. 13945
    Prev
    Next
    INDEX
    Explanations

    and subsequent actions

    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
    :[],
    -1.33
    FromNib
    -1.12
     niektor
    -1.10
    IEnumerator
    -1.09
    anolamine
    -1.08
     valamint
    -1.04
    EqualsAnd
    -1.02
    :{
    -1.02
    ":{
    -1.01
     niečo
    -0.99
    POSITIVE LOGITS
     then
    2.33
     later
    2.11
     since
    1.65
     subsequently
    1.57
     shortly
    1.51
     immediately
    1.36
     soon
    1.34
     thereafter
    1.32
     subsequent
    1.30
     continued
    1.23
    Activations Density 0.058%

    No Known Activations