© 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. 72620
    Prev
    Next
    INDEX
    Explanations

    located in or near a place

    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
     then
    -1.53
     each
    -1.41
     all
    -1.35
     so
    -1.16
     various
    -1.13
     possano
    -1.12
    then
    -1.12
     some
    -1.11
     entonces
    -1.08
     hingegen
    -1.06
    POSITIVE LOGITS
     momente
    1.35
     genoux
    1.10
     neutre
    1.09
     huid
    1.05
    遑
    1.01
    怎么会
    0.97
     bandoulière
    0.97
     domésticos
    0.96
    yaç
    0.96
     amanecer
    0.96
    Activations Density 0.402%

    No Known Activations