© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40160
    Prev
    Next
    INDEX
    Explanations

    kernel size and Q

    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
     +
    -1.13
    }
    -1.13
     +=
    -1.09
    ],
    -1.08
     easy
    -1.05
    while
    -1.03
    While
    -1.03
    就像是
    -1.03
    ものの
    -1.03
     Ingenie
    -1.02
    POSITIVE LOGITS
    GRAT
    1.18
     paparazzi
    1.13
     geschickt
    1.09
    Kappa
    1.06
     derselbe
    1.05
    ensivo
    1.05
    América
    1.05
    ZIN
    1.04
     nástro
    1.04
     capacitación
    1.04
    Activations Density 0.001%

    No Known Activations