© 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. 75610
    Prev
    Next
    INDEX
    Explanations

    movie title and genre

    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
     skóra
    -0.80
     Moles
    -0.75
    andafter
    -0.74
    siana
    -0.74
     hlad
    -0.74
     correspondent
    -0.73
    toad
    -0.73
    antigua
    -0.72
    amuk
    -0.71
    ложении
    -0.71
    POSITIVE LOGITS
     popularity
    0.96
    original
    0.90
     adult
    0.86
    adult
    0.85
    vote
    0.84
    budget
    0.82
    Adult
    0.82
     original
    0.81
    Budget
    0.79
     MediaType
    0.79
    Activations Density 0.002%

    No Known Activations