© 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. 10-GEMMASCOPE-RES-131K
    7. 47585
    Prev
    Next
    INDEX
    Explanations

    imitation, copy, killer, defeat

    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_10/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
     and
    -1.80
     including
    -1.41
     revêtement
    -1.36
    inerario
    -1.23
    ophyllum
    -1.20
    åde
    -1.17
    ",
    -1.16
    ographed
    -1.16
    tored
    -1.15
     入っ
    -1.15
    POSITIVE LOGITS
    分で
    1.09
    続く
    1.09
     didn
    1.09
     nobody
    1.07
     gostaria
    1.06
     pousada
    1.05
     every
    1.05
    ன
    1.04
     started
    1.04
     many
    1.03
    Activations Density 0.072%

    No Known Activations