© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109868
    Prev
    Next
    INDEX
    Explanations

    public class modifiers

    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
    esub
    -1.05
     JAXBElement
    -1.00
    できません
    -0.97
     luzes
    -0.96
    struk
    -0.96
     ladr
    -0.95
    endung
    -0.93
    albeit
    -0.91
     開催
    -0.91
    ㅿ
    -0.91
    POSITIVE LOGITS
    is
    1.15
    ol
    1.02
    fo
    1.00
    kal
    0.94
    ce
    0.94
    in
    0.93
    os
    0.92
    like
    0.92
    素晴らしい
    0.91
    ot
    0.91
    Activations Density 0.005%

    No Known Activations