© 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. 37984
    Prev
    Next
    INDEX
    Explanations

    good or bad

    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
    オススメです
    -1.02
    おすすめです
    -0.85
    aby
    -0.85
     Orts
    -0.80
    mathrm
    -0.80
    lization
    -0.79
    xref
    -0.77
    ój
    -0.75
    apé
    -0.74
    zondere
    -0.74
    POSITIVE LOGITS
     good
    4.16
    good
    3.25
    Good
    3.06
     Good
    2.88
    GOOD
    2.73
     GOOD
    2.67
     positive
    2.61
     both
    2.36
     successes
    2.08
     zarówno
    2.05
    Activations Density 0.111%

    No Known Activations