© 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. 54234
    Prev
    Next
    INDEX
    Explanations

    cry aloud

    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
    了一会儿
    -0.85
     REACH
    -0.84
    Indian
    -0.79
     premieres
    -0.76
     errMsg
    -0.76
     INR
    -0.74
     Wikiquote
    -0.74
     보기
    -0.74
     fag
    -0.73
     VIVO
    -0.73
    POSITIVE LOGITS
     twice
    1.07
    twice
    0.93
    称
    0.91
    continuous
    0.80
     two
    0.77
    Siren
    0.76
    ឋ
    0.76
     Contin
    0.72
    Twice
    0.72
     Lowe
    0.72
    Activations Density 0.007%

    No Known Activations