© 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. 73387
    Prev
    Next
    INDEX
    Explanations

    verbs followed by descriptors

    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
    -1.40
     it
    -1.31
    vább
    -1.24
    these
    -1.16
    again
    -1.13
     its
    -1.10
    从此
    -1.10
    である
    -1.09
    astify
    -1.07
    はこの
    -1.04
    POSITIVE LOGITS
     always
    1.23
     anklicken
    1.18
     äl
    1.13
     flesta
    1.11
     überall
    1.09
     cucchiaio
    1.09
     lorsqu
    1.06
     всегда
    1.04
     enggak
    1.04
    ึกษา
    1.02
    Activations Density 0.018%

    No Known Activations