© 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. 34-GEMMASCOPE-RES-131K
    7. 63400
    Prev
    Next
    INDEX
    Explanations

    credibility and legitimacy

    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
     FormBuilder
    -0.85
    registered
    -0.81
    ίου
    -0.80
     klassi
    -0.77
     памят
    -0.77
    stornos
    -0.75
    ンピース
    -0.75
     bedeutet
    -0.73
    hiana
    -0.73
     Conservatory
    -0.73
    POSITIVE LOGITS
     credibility
    4.22
     legitimacy
    3.50
    credi
    2.80
     credi
    2.53
     authority
    2.44
     credible
    2.36
     legitim
    2.06
     legiti
    1.95
    authority
    1.88
    Cre
    1.84
    Activations Density 0.029%

    No Known Activations