© 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. 84725
    Prev
    Next
    INDEX
    Explanations

    pressing the back button

    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
    醒来
    -0.87
    过来了
    -0.85
    žka
    -0.84
    btnNew
    -0.84
     menegaskan
    -0.83
    pylab
    -0.83
    loginButton
    -0.82
    PlayerPrefs
    -0.81
    ॲ
    -0.80
    OfDay
    -0.79
    POSITIVE LOGITS
     back
    5.41
    Back
    3.70
    back
    3.59
     Back
    3.56
     BACK
    3.41
    BACK
    3.30
     zurück
    3.23
     return
    2.97
     terug
    2.92
     назад
    2.81
    Activations Density 0.032%

    No Known Activations