© 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. 12273
    Prev
    Next
    INDEX
    Explanations

    quality assessment

    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
    Rozmiar
    -0.81
     красивые
    -0.81
    Wise
    -0.81
    weis
    -0.76
    hemm
    -0.76
    ДО
    -0.75
     hasilnya
    -0.75
    čius
    -0.75
    üng
    -0.74
    arzt
    -0.74
    POSITIVE LOGITS
     good
    4.84
     excellent
    4.19
     poor
    3.09
    good
    3.03
     better
    2.88
    Excellent
    2.83
    excellent
    2.78
     Excellent
    2.70
     хоро
    2.69
     decent
    2.63
    Activations Density 0.183%

    No Known Activations