© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19110
    Prev
    Next
    INDEX
    Explanations

    index arrays, slices, boolean

    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
     their
    -1.56
    ônus
    -1.33
     each
    -1.31
    endforeach
    -1.25
    哧
    -1.24
    itizing
    -1.17
     facendo
    -1.16
    更多
    -1.16
    お菓子
    -1.16
     senhora
    -1.14
    POSITIVE LOGITS
    nossa
    1.41
     даже
    1.34
    Also
    1.31
    ämään
    1.30
    сю
    1.29
    Podemos
    1.25
    ἵ
    1.25
    ikasi
    1.25
    Médaille
    1.23
    чера
    1.23
    Activations Density 0.165%

    No Known Activations