© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41927
    Prev
    Next
    INDEX
    Explanations

    issues and problems

    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
     to
    -2.31
     by
    -1.81
     the
    -1.66
     of
    -1.46
    了不少
    -1.33
    ]
    -1.27
    by
    -1.26
     various
    -1.26
     was
    -1.24
     not
    -1.24
    POSITIVE LOGITS
    อีก
    1.55
     again
    1.51
    sproble
    1.50
    wolle
    1.43
     celebrid
    1.38
    breng
    1.37
    Opere
    1.37
     AGAIN
    1.36
     pegatina
    1.36
     opět
    1.35
    Activations Density 0.077%

    No Known Activations