© 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. 130587
    Prev
    Next
    INDEX
    Explanations

    who questions

    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
     également
    -1.46
    }}$
    -1.32
     also
    -1.27
    Something
    -1.16
     internacionais
    -1.15
     również
    -1.14
     Affiliations
    -1.13
     نیز
    -1.13
    }$
    -1.11
    Anything
    -1.11
    POSITIVE LOGITS
     their
    1.86
     توانند
    1.40
    彼らの
    1.39
     leurs
    1.29
     themselves
    1.28
     then
    1.27
     there
    1.25
    得上
    1.25
    tarta
    1.24
     hinauf
    1.24
    Activations Density 0.041%

    No Known Activations