© 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. 108895
    Prev
    Next
    INDEX
    Explanations

    really, really, actually, kind

    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
     hiçbir
    -1.06
    这类
    -1.04
    “……”
    -1.02
     cerveja
    -1.02
    lindungi
    -1.00
     keinen
    -1.00
    红的
    -0.99
     بعضی
    -0.99
    心に
    -0.99
    気がする
    -0.98
    POSITIVE LOGITS
     really
    2.56
     sort
    1.94
    really
    1.93
    Really
    1.92
     davvero
    1.83
     realmente
    1.80
     kind
    1.72
     actually
    1.71
     perhaps
    1.63
     Really
    1.53
    Activations Density 0.011%

    No Known Activations