© 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. 45205
    Prev
    Next
    INDEX
    Explanations

    going to a specific location

    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
     both
    -1.60
     Zugriff
    -1.29
     vissa
    -1.26
     lavable
    -1.23
     particular
    -1.23
    ..\..\
    -1.22
    无数
    -1.22
     méxico
    -1.22
     отдельных
    -1.21
     milj
    -1.20
    POSITIVE LOGITS
     where
    2.14
     Cualquier
    1.38
    Ayrıca
    1.32
    Kaynakça
    1.30
    ˂
    1.26
     who
    1.26
    friday
    1.25
    
    1.25
     Había
    1.24
    ='';
    1.24
    Activations Density 0.154%

    No Known Activations