© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48998
    Prev
    Next
    INDEX
    Explanations

    circles and values

    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
     magnética
    -0.79
     valutazione
    -0.78
    orphic
    -0.77
     Kennt
    -0.77
    ]]=
    -0.76
     amarilla
    -0.76
    alie
    -0.75
     Behaup
    -0.75
    spli
    -0.75
     full
    -0.74
    POSITIVE LOGITS
     come
    1.59
     comes
    1.48
     circle
    1.38
     came
    1.31
     Come
    1.17
    Come
    1.15
    Circle
    1.14
    circle
    1.13
    come
    1.13
    comes
    1.13
    Activations Density 0.005%

    No Known Activations