© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33759
    Prev
    Next
    INDEX
    Explanations

    contrast and concession

    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
    preferably
    -1.15
    unfortunately
    -1.14
    rably
    -1.07
    various
    -1.05
    夸张
    -1.02
    hopefully
    -1.02
     interieur
    -1.00
    ybė
    -1.00
     अच्छ
    -0.98
    official
    -0.98
    POSITIVE LOGITS
     it
    1.64
     beneficial
    1.63
     helpful
    1.63
     not
    1.62
     difficult
    1.62
     impossible
    1.56
     easier
    1.56
     advantageous
    1.55
     necessary
    1.51
     doable
    1.51
    Activations Density 0.105%

    No Known Activations