© 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. 10-GEMMASCOPE-RES-131K
    7. 86167
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
     vencedor
    -1.46
    Normdaten
    -1.44
    Är
    -1.42
     a
    -1.40
    نوش
    -1.38
     sebagaimana
    -1.38
     NÃO
    -1.35
    也就是
    -1.32
    总是
    -1.30
     могли
    -1.30
    POSITIVE LOGITS
     there
    2.27
     they
    1.98
     different
    1.91
     we
    1.90
    ],'
    1.82
    zembro
    1.76
    も行
    1.70
    junctive
    1.69
    ],\
    1.68
    cursions
    1.64
    Activations Density 0.015%

    No Known Activations