© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31768
    Prev
    Next
    INDEX
    Explanations

    really [specific thing]

    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
     ControllerBase
    -0.93
     exportaciones
    -0.86
     مدرن
    -0.82
    zow
    -0.79
    DCHECK
    -0.79
     takiej
    -0.79
    ricane
    -0.78
    kozá
    -0.76
     gerade
    -0.76
    นะครับ
    -0.76
    POSITIVE LOGITS
     really
    6.09
    really
    4.53
    Really
    4.47
     Really
    3.84
     realmente
    3.33
     vraiment
    3.28
     wirklich
    2.92
     davvero
    2.73
    真的
    2.64
     realy
    2.61
    Activations Density 0.104%

    No Known Activations