© 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. 65985
    Prev
    Next
    INDEX
    Explanations

    realization that

    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
     here
    -1.37
     aici
    -1.16
    gives
    -1.06
     aceste
    -1.06
     solcher
    -1.05
     entered
    -1.02
     diferite
    -1.02
     nimic
    -1.02
     numai
    -1.00
     nevoie
    -1.00
    POSITIVE LOGITS
     that
    1.72
     realizes
    1.13
    cticas
    1.07
     realises
    1.05
     belated
    1.05
     realisation
    1.05
     realize
    1.04
    Other
    1.03
     to
    1.02
     remembrance
    1.02
    Activations Density 0.017%

    No Known Activations