© 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. 66252
    Prev
    Next
    INDEX
    Explanations

    keeping and cultivation

    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
    yní
    -0.84
    成长
    -0.83
    ductor
    -0.82
    }^{+}\
    -0.80
    lient
    -0.76
     iguales
    -0.76
     gebaut
    -0.75
     ARCHITECTURE
    -0.75
     henvisninger
    -0.75
    γγ
    -0.74
    POSITIVE LOGITS
     kept
    2.80
     keeping
    2.45
    Keeping
    2.14
     Keeping
    2.13
    keeping
    2.13
     keep
    2.03
     Kept
    1.96
    kept
    1.89
     keeper
    1.88
    Keep
    1.83
    Activations Density 0.052%

    No Known Activations