© 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. 105761
    Prev
    Next
    INDEX
    Explanations

    identifying sameness or similarity

    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
    鸶
    -1.65
    聍
    -1.40
     заменить
    -1.38
    sified
    -1.37
    もちゃ
    -1.32
    नलोड
    -1.30
    ätzen
    -1.27
    脔
    -1.27
     tomto
    -1.27
    </b>
    -1.25
    POSITIVE LOGITS
     previsto
    1.32
     that
    1.25
     they
    1.25
    一样的
    1.24
     applies
    1.24
     celebrates
    1.24
     like
    1.23
     their
    1.22
     thier
    1.20
     coincides
    1.16
    Activations Density 0.225%

    No Known Activations