© 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. 99038
    Prev
    Next
    INDEX
    Explanations

    Bigg Boss contestants

    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
     Wils
    -0.77
    Begriffsklä
    -0.76
    úly
    -0.74
    ínas
    -0.72
    millis
    -0.72
     géné
    -0.71
    ៖
    -0.71
     nuestros
    -0.71
     szere
    -0.69
     Okinawa
    -0.69
    POSITIVE LOGITS
     contestant
    1.34
     contestants
    1.24
     evicted
    1.09
     Bigg
    1.09
     inside
    1.08
     eviction
    1.05
     captain
    1.03
     nominate
    0.94
    Bigg
    0.94
    participants
    0.93
    Activations Density 0.005%

    No Known Activations