© 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. 38520
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
     or
    -1.42
     this
    -1.23
     its
    -1.19
     itself
    -1.10
     at
    -1.03
    它
    -1.03
     likewise
    -1.02
     from
    -0.98
     conversely
    -0.98
     another
    -0.94
    POSITIVE LOGITS
    respectively
    1.62
     respectively
    1.37
     jeweils
    1.23
     respectivamente
    1.20
     leurs
    1.17
     Эти
    1.13
    分别
    1.12
    それぞれ
    1.10
     respectivement
    1.09
     모두
    1.08
    Activations Density 0.024%

    No Known Activations