© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4342
    Prev
    Next
    INDEX
    Explanations

    monthly archives

    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
    pecially
    -1.01
    становка
    -0.98
     EVEN
    -0.94
    kose
    -0.90
     règles
    -0.89
    Τ
    -0.89
    THERE
    -0.87
    mao
    -0.87
    tahanan
    -0.86
     specif
    -0.85
    POSITIVE LOGITS
     from
    0.88
    Cruel
    0.80
    ЦИИ
    0.79
     rims
    0.79
    実際
    0.78
    Flaming
    0.78
    )],
    0.77
    Burial
    0.76
    Injured
    0.76
    ?>"
    0.75
    Activations Density 0.008%

    No Known Activations