© 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. 45296
    Prev
    Next
    INDEX
    Explanations

    upper/lower case transformations

    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
     Pavlov
    -0.72
    레스
    -0.72
    Constantes
    -0.66
     vag
    -0.65
     Pelle
    -0.65
    пкой
    -0.65
    ましょう
    -0.65
     hoch
    -0.64
    xdd
    -0.64
     Nordic
    -0.63
    POSITIVE LOGITS
     case
    4.63
    case
    4.06
    Case
    3.80
     Case
    3.59
     cases
    3.36
    CASE
    2.88
     CASE
    2.84
    cases
    2.80
     Cases
    2.78
    Cases
    2.69
    Activations Density 0.036%

    No Known Activations