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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129805
    Prev
    Next
    INDEX
    Explanations

    again and now

    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_22/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
     frecuentemente
    -0.91
    弭
    -0.90
     échou
    -0.89
     défend
    -0.85
    ってました
    -0.82
     cucharadita
    -0.80
    场所
    -0.80
     первая
    -0.79
    ANGAN
    -0.79
     algunos
    -0.79
    POSITIVE LOGITS
     now
    2.69
     again
    2.48
    again
    1.84
     today
    1.81
    今回も
    1.78
    今度は
    1.70
     ahora
    1.66
     다시
    1.65
    now
    1.62
    Again
    1.61
    Activations Density 0.145%

    No Known Activations