© 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. 47972
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    gevens
    -0.87
    ：……
    -0.82
     esquer
    -0.78
     ghz
    -0.78
    moj
    -0.77
     আম
    -0.77
    ꪔ
    -0.77
    костюм
    -0.77
    ensioni
    -0.76
     preservative
    -0.74
    POSITIVE LOGITS
     Fifty
    0.81
     another
    0.77
     sixty
    0.77
    Masukkan
    0.76
    Ρ
    0.73
    Ά
    0.73
    concrete
    0.72
    高雄
    0.71
    viewtopic
    0.71
     wing
    0.71
    Activations Density 0.022%

    No Known Activations