© 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. 67602
    Prev
    Next
    INDEX
    Explanations

    unidimensional or unidirectional

    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
    O
    -3.73
    寕
    -3.45
     ausein
    -3.39
    ing
    -3.09
    鷙
    -3.08
    悭
    -3.06
     αλλά
    -3.06
    }$
    -3.05
    埽
    -3.00
    鍇
    -2.98
    POSITIVE LOGITS
     ayudar
    2.91
    呦
    2.84
     expanse
    2.81
    榦
    2.73
    本章
    2.53
    够了
    2.52
    嗚
    2.50
     analyse
    2.48
    一会
    2.45
    当下
    2.38
    Activations Density 0.017%

    No Known Activations