© 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. 59082
    Prev
    Next
    INDEX
    Explanations

    code documentation comments

    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
     wartawan
    -0.88
    asari
    -0.82
    мання
    -0.81
    ært
    -0.74
     Rapper
    -0.73
    metingen
    -0.72
     veículo
    -0.71
     Dickerson
    -0.69
    Modifier
    -0.68
    narod
    -0.68
    POSITIVE LOGITS
     tarihinde
    0.80
    remarks
    0.79
    setOnItem
    0.77
    Normals
    0.77
    ktır
    0.76
    throw
    0.75
     bersi
    0.75
    étaire
    0.75
    !);
    0.74
     labyrinth
    0.74
    Activations Density 0.008%

    No Known Activations