© 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. 33854
    Prev
    Next
    INDEX
    Explanations

    Microarray, Standard dose, Q:, The invention

    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
     at
    -1.34
    Ķ
    -1.28
     epitom
    -1.25
     without
    -1.23
     együtt
    -1.22
    𝐒
    -1.22
     profoundly
    -1.20
     after
    -1.20
     perpetually
    -1.20
     when
    -1.19
    POSITIVE LOGITS
    7
    1.52
     opulent
    1.47
    3
    1.45
    8
    1.42
     magnificent
    1.41
     Begriffe
    1.41
    4
    1.40
     grumpy
    1.39
     myriad
    1.39
     vários
    1.39
    Activations Density 0.011%

    No Known Activations