© 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. 66155
    Prev
    Next
    INDEX
    Explanations

    things coming in

    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
     ognuno
    -0.80
    ppet
    -0.73
    に移
    -0.73
    mpl
    -0.71
    返す
    -0.70
    ríamos
    -0.69
     最後
    -0.69
     行っ
    -0.68
    –
    -0.68
     بهار
    -0.67
    POSITIVE LOGITS
     coming
    3.41
     come
    3.14
     arrive
    3.11
     came
    2.98
     arrives
    2.94
     arriving
    2.75
     arrived
    2.73
     comes
    2.70
    Coming
    2.42
    coming
    2.38
    Activations Density 0.084%

    No Known Activations