© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    we are a/an

    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
     those
    -1.47
     where
    -1.45
     with
    -1.44
     why
    -1.43
    jauh
    -1.36
     when
    -1.33
     wollt
    -1.26
    姗
    -1.24
    位的
    -1.21
    ҵ
    -1.20
    POSITIVE LOGITS
    }
    1.42
     stuks
    1.34
     belajar
    1.27
    であり
    1.27
    inth
    1.24
     are
    1.23
    cellor
    1.21
    out
    1.21
    ów
    1.18
    inthe
    1.17
    Activations Density 0.063%

    No Known Activations