© 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. 22-GEMMASCOPE-RES-131K
    7. 25309
    Prev
    Next
    INDEX
    Explanations

    technical terms and annotations

    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_22/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
    ərb
    -0.91
     Kapelle
    -0.83
    טר
    -0.79
    続け
    -0.78
    lafen
    -0.77
     HDF
    -0.77
     initState
    -0.77
    ństw
    -0.76
    fört
    -0.74
     рождения
    -0.73
    POSITIVE LOGITS
    PutMapping
    1.01
     cammin
    0.87
     aggiorn
    0.85
     marrone
    0.85
     soffer
    0.84
    ixeira
    0.83
     ricev
    0.82
     indipendente
    0.82
     specchio
    0.81
    修改
    0.80
    Activations Density 0.001%

    No Known Activations