© 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. 26806
    Prev
    Next
    INDEX
    Explanations

    according to sources

    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
     kini
    -1.08
    lokasi
    -1.07
     vinil
    -1.06
     smuggled
    -1.05
     vinyle
    -1.04
     misinterpreted
    -1.02
     mikrofon
    -1.00
    plz
    -0.99
     trimestre
    -0.99
    setNome
    -0.99
    POSITIVE LOGITS
     earlier
    1.52
     website
    1.40
     later
    1.28
     said
    1.23
     previous
    1.22
     previously
    1.11
     online
    1.09
     added
    1.09
     according
    1.02
     video
    1.00
    Activations Density 0.016%

    No Known Activations