© 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. 26705
    Prev
    Next
    INDEX
    Explanations

    booking website information

    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
     their
    -1.52
     develop
    -1.30
     his
    -1.25
     large
    -1.22
     being
    -1.19
     my
    -1.16
    )=>{
    -1.16
     require
    -1.15
     primeras
    -1.14
     sampai
    -1.11
    POSITIVE LOGITS
    颚
    1.47
    ἶ
    1.27
    НИМА
    1.26
    頜
    1.22
     najdete
    1.20
     étage
    1.20
    𓏸
    1.20
     Selecciona
    1.18
    minyak
    1.17
    ulitis
    1.16
    Activations Density 0.011%

    No Known Activations