© 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. 91207
    Prev
    Next
    INDEX
    Explanations

    project activities and implementation

    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
    гән
    -0.90
    Поль
    -0.90
    ()}>
    -0.89
    kelijk
    -0.85
    })();
    -0.84
    effectuer
    -0.84
    viewWillAppear
    -0.82
    iyle
    -0.81
     Gottesdienst
    -0.81
    VARS
    -0.80
    POSITIVE LOGITS
     activities
    2.23
     interventions
    1.91
    activities
    1.68
     intervention
    1.63
     ACTIVITIES
    1.59
     implementation
    1.51
     components
    1.41
     implemented
    1.40
     actividades
    1.39
     implement
    1.38
    Activations Density 0.018%

    No Known Activations