© 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. 31844
    Prev
    Next
    INDEX
    Explanations

    pure prefix to brands/qualities

    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
     actuales
    -0.97
    Jeans
    -0.96
     diferentes
    -0.94
     crappy
    -0.93
     pomi
    -0.93
    摀
    -0.90
     üb
    -0.89
    atized
    -0.88
     нового
    -0.87
     várias
    -0.87
    POSITIVE LOGITS
    Pure
    2.20
     Pure
    2.05
    pure
    2.02
     pure
    1.93
    PURE
    1.52
     纯
    1.41
    bred
    1.39
    純
    1.39
    纯
    1.37
     murni
    1.34
    Activations Density 0.017%

    No Known Activations