© 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. 103003
    Prev
    Next
    INDEX
    Explanations

    enumerated list items in parentheses

    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
     and
    -0.91
     задний
    -0.87
    マイズ
    -0.83
     lalu
    -0.82
    encu
    -0.82
    Ehrungen
    -0.81
     赤ちゃん
    -0.81
     soc
    -0.81
    似的
    -0.81
     Those
    -0.80
    POSITIVE LOGITS
     unless
    1.16
     if
    1.05
     except
    1.00
     utiles
    0.96
     insofar
    0.93
     is
    0.90
    except
    0.90
    FormComponent
    0.83
     если
    0.83
    unless
    0.81
    Activations Density 0.013%

    No Known Activations