© 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. 65111
    Prev
    Next
    INDEX
    Explanations

    comparing, after he, in games, shock, second position

    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
     memakan
    -1.04
     باعث
    -0.98
     said
    -0.97
    里的
    -0.96
     tells
    -0.94
     found
    -0.93
     memakai
    -0.93
     choisi
    -0.91
     meant
    -0.90
     ấy
    -0.90
    POSITIVE LOGITS
     commenced
    1.11
     commences
    1.05
     commencing
    0.97
     erforderlich
    0.94
    而言
    0.93
     концеп
    0.91
    )^{-
    0.91
     utilized
    0.91
    }}\
    0.89
     insbesondere
    0.88
    Activations Density 0.051%

    No Known Activations