© 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. 34-GEMMASCOPE-RES-131K
    7. 69937
    Prev
    Next
    INDEX
    Explanations

    certain words followed by verbs or punctuation

    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
     العديد
    -1.24
     heretofore
    -1.16
    overall
    -1.09
     somente
    -1.08
     wcześniej
    -1.06
    ınıza
    -1.03
     намного
    -1.03
     информация
    -1.02
     jedoch
    -1.02
     valamint
    -1.01
    POSITIVE LOGITS
     alike
    1.02
     occasional
    0.96
     impulso
    0.93
     everywhere
    0.93
     activo
    0.91
    supset
    0.91
     vaguely
    0.89
     exige
    0.88
     frankly
    0.87
     vague
    0.86
    Activations Density 0.020%

    No Known Activations