© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72420
    Prev
    Next
    INDEX
    Explanations

    degrees and professional qualifications

    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
     when
    -1.66
     again
    -1.44
     time
    -1.42
     for
    -1.41
     specific
    -1.34
     things
    -1.30
     midway
    -1.29
     usable
    -1.26
     four
    -1.23
     halfway
    -1.22
    POSITIVE LOGITS
     SUCH
    1.32
    骉
    1.31
    妧
    1.30
    Started
    1.24
    𓁹
    1.22
     Ministre
    1.21
     aussit
    1.20
     /><
    1.20
     lutter
    1.18
     Réalisation
    1.17
    Activations Density 0.130%

    No Known Activations