© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58543
    Prev
    Next
    INDEX
    Explanations

    behind or the reason for

    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_10/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
     have
    -2.05
     was
    -1.70
    *
    -1.66
     if
    -1.57
    "'
    -1.51
    _
    -1.50
     wer
    -1.45
     mencion
    -1.42
     has
    -1.41
     p
    -1.40
    POSITIVE LOGITS
     detrás
    1.84
     derrière
    1.68
     behind
    1.63
     rationale
    1.52
     baskılı
    1.48
    hlte
    1.48
     oferece
    1.47
     cuadrada
    1.46
     Behind
    1.45
    此事
    1.45
    Activations Density 0.030%

    No Known Activations