© 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. 86769
    Prev
    Next
    INDEX
    Explanations

    adding and editor metadata

    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
    rends
    -0.74
     Lama
    -0.73
     Mojo
    -0.72
     До
    -0.70
     uni
    -0.68
     スイ
    -0.66
     досто
    -0.66
     geo
    -0.66
     Reyn
    -0.66
    배
    -0.66
    POSITIVE LOGITS
     Templo
    0.76
    textField
    0.75
     שר
    0.74
    記載
    0.72
    Conversely
    0.69
    artner
    0.69
     Quantification
    0.68
    🖋
    0.68
     innermost
    0.68
    Elf
    0.68
    Activations Density 0.078%

    No Known Activations