© 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. 34-GEMMASCOPE-RES-131K
    7. 106824
    Prev
    Next
    INDEX
    Explanations

    Laravel code comments

    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
    Holstein
    -0.90
    一样的
    -0.88
     pintores
    -0.84
     all
    -0.81
     Haben
    -0.80
     jaké
    -0.80
    Lycka
    -0.79
    UQ
    -0.79
    ルター
    -0.78
    девушка
    -0.78
    POSITIVE LOGITS
     ἐκ
    1.03
    Discussion
    0.77
     เรา
    0.76
     მ
    0.75
    FormControl
    0.74
     τὰ
    0.74
     αὐτ
    0.74
    av
    0.73
    ITAR
    0.73
     तरह
    0.73
    Activations Density 0.005%

    No Known Activations