© 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. 66235
    Prev
    Next
    INDEX
    Explanations

    remember your workshop location

    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
    conhe
    -1.16
     Instead
    -1.07
     кухня
    -1.05
     fakty
    -1.04
     которое
    -1.04
     Commencez
    -1.04
    Immediately
    -1.02
    kazuje
    -1.01
    Instead
    -1.00
     plutôt
    -0.99
    POSITIVE LOGITS
     your
    1.63
     only
    1.27
     this
    1.17
     always
    1.09
     also
    1.08
     you
    1.08
    ただの
    1.06
    ovala
    1.06
    Remember
    1.06
    あく
    1.03
    Activations Density 0.016%

    No Known Activations