© 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. 66166
    Prev
    Next
    INDEX
    Explanations

    people and services

    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
    骷
    -0.78
    Вид
    -0.75
     can
    -0.75
    oplus
    -0.74
    Ḥ
    -0.71
     franch
    -0.71
     относительно
    -0.70
    阵容
    -0.70
     remediation
    -0.69
    dollis
    -0.69
    POSITIVE LOGITS
    BL
    0.95
     powders
    0.90
     BL
    0.84
    [#
    0.81
     夹
    0.78
     dunno
    0.76
     passare
    0.75
    形成
    0.75
    ゼル
    0.75
    uality
    0.74
    Activations Density 0.004%

    No Known Activations