© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55610
    Prev
    Next
    INDEX
    Explanations

    be made available

    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
    يقة
    -0.96
     supposedly
    -0.93
     which
    -0.92
    きたいと思います
    -0.91
     possibly
    -0.90
     Nascimento
    -0.89
    ッテリー
    -0.88
    鍰
    -0.88
    犧
    -0.88
    ắc
    -0.88
    POSITIVE LOGITS
     a
    1.90
     espíritu
    0.88
    ub
    0.87
     domínio
    0.85
    扯
    0.85
    のに
    0.84
     എ
    0.83
     null
    0.82
     solange
    0.82
     Monaten
    0.81
    Activations Density 0.003%

    No Known Activations