© 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. 68798
    Prev
    Next
    INDEX
    Explanations

    optimized, studied, examined, determined

    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
     for
    -1.46
     欣赏
    -1.32
     from
    -1.29
    WithMany
    -1.27
    udière
    -1.10
     todėl
    -1.10
     gedacht
    -1.09
     are
    -1.09
    }*/
    -1.09
    inian
    -1.09
    POSITIVE LOGITS
     its
    1.24
     autre
    1.20
     despite
    1.20
    otherwise
    1.19
    彼女の
    1.16
    咂
    1.14
    certain
    1.09
     while
    1.09
    As
    1.07
     previous
    1.06
    Activations Density 0.278%

    No Known Activations