© 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. 34841
    Prev
    Next
    INDEX
    Explanations

    date and comparison

    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
     reseña
    -0.85
    卺
    -0.84
    jugend
    -0.82
    CardModule
    -0.81
    geset
    -0.77
     kawaida
    -0.77
     APPLICABLE
    -0.77
    ={`
    -0.77
    ]<<"
    -0.76
    ctively
    -0.76
    POSITIVE LOGITS
     there
    1.05
     slightly
    0.96
     even
    0.93
    𝒩
    0.89
     around
    0.88
    sightly
    0.88
     Wartawan
    0.81
    cets
    0.79
    idać
    0.79
     next
    0.77
    Activations Density 0.015%

    No Known Activations