© 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. 34-GEMMASCOPE-RES-131K
    7. 115612
    Prev
    Next
    INDEX
    Explanations

    because

    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_34/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
    ᵖ
    -1.27
    よりは
    -1.22
    íguez
    -1.20
     BoxFit
    -1.15
    Răsp
    -1.09
    }]
    -1.09
    ുകൾ
    -1.09
    pielt
    -1.09
     tedy
    -1.08
     équipement
    -1.07
    POSITIVE LOGITS
     because
    10.25
     porque
    6.47
     потому
    6.03
    Because
    6.00
    因为
    5.94
    because
    5.75
    因為
    5.63
     Because
    5.53
     perché
    5.31
     karena
    4.97
    Activations Density 0.616%

    No Known Activations