© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73124
    Prev
    Next
    INDEX
    Explanations

    promise chaining

    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
     saati
    -1.25
     mikrofon
    -1.22
     autobus
    -1.21
     itali
    -1.21
     ekst
    -1.20
     annen
    -1.19
     profesion
    -1.17
     atlet
    -1.17
     menyen
    -1.14
    ⎘
    -1.14
    POSITIVE LOGITS
     or
    1.52
    ,
    1.21
     many
    1.16
     otherwise
    1.16
     time
    1.11
     F
    1.09
    L
    1.08
     T
    1.05
     commonly
    1.04
    t
    1.04
    Activations Density 0.000%

    No Known Activations