© 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. 106675
    Prev
    Next
    INDEX
    Explanations

    going round in circles

    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
    хра
    -0.79
    borgs
    -0.68
    腼
    -0.68
     興
    -0.66
    󠁿
    -0.66
     berupa
    -0.65
    ∊
    -0.65
     objectAtIndex
    -0.63
    Ceramic
    -0.63
    時半
    -0.63
    POSITIVE LOGITS
     circles
    5.81
     circle
    4.41
    circles
    4.38
     Circles
    4.16
    Circles
    3.89
    circle
    3.75
     círculos
    3.42
     Circle
    3.36
    Circle
    3.30
    CIRCLE
    3.06
    Activations Density 0.031%

    No Known Activations